From ac796945a473cc7731442732d5478a748b7437e0 Mon Sep 17 00:00:00 2001
From: CoolBoy <2269097679@qq.com>
Date: Sun, 20 Sep 2026 03:09:19 +0000
Subject: [PATCH] state: generation 10109 (result)

---
 .modelhub_state/recovery_intents.jsonl    | 200 +++++++++++-----------
 .modelhub_state/routing_intelligence.json |  36 ++--
 ledger/submissions.jsonl                  | 100 +++++++++++
 manifest.json                             |  14 +-
 outcomes/submissions.jsonl                | 100 +++++++++++
 5 files changed, 326 insertions(+), 124 deletions(-)

diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 2b1ede8b3b..1290c62e4d 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -1059,106 +1059,106 @@
 {"batchId": "3efb2f9a71c744cbb0e6630a47a68d75", "completedAt": "2026-09-20T02:52:52.464004+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T02:52:42.428783+00:00", "framework": "vllm", "intentId": "5bb6e6295b8a49809bfeac45bd288077", "lastModified": "2026-08-29T05:55:46+00:00", "modelAddress": "https://modelscope.cn/models/ysqlian/YZH_Model", "reason": null, "reconciledAt": "2026-09-20T03:07:39.990817+00:00", "repoId": "ysqlian/YZH_Model", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4969092", "taskType": "text-generation"}
 {"batchId": "3efb2f9a71c744cbb0e6630a47a68d75", "completedAt": "2026-09-20T02:52:52.464007+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T02:52:42.428858+00:00", "framework": "vllm", "intentId": "5829d73d0a2c40bc9e926f2ef0a41085", "lastModified": "2026-08-27T04:11:21+00:00", "modelAddress": "https://modelscope.cn/models/dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "reason": null, "reconciledAt": "2026-09-20T03:07:39.990351+00:00", "repoId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4969090", "taskType": "text-generation"}
 {"batchId": "3efb2f9a71c744cbb0e6630a47a68d75", "completedAt": "2026-09-20T02:52:52.464009+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T02:52:42.428929+00:00", "framework": "vllm", "intentId": "d7fd7cbe032648afbdb2c7414e63fe56", "lastModified": "2026-08-28T13:00:18+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-guardian-4.1-8b", "reason": null, "reconciledAt": "2026-09-20T03:07:39.989099+00:00", "repoId": "ibm-granite/granite-guardian-4.1-8b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4969093", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728716+00:00", "framework": "vllm_tokenizer_patch", "intentId": "857a84b7853e4d5bb04bb032504dbd4d", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728844+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1c0eafd25e77420982c236f8b5e580dc", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a3ff2e6ca8314647889e924ea9c6e25b", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728949+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5b74096d09b49b5b6c798886e516a3e", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "82dddaf14d5a426c80cf26e2d14a4664", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729048+00:00", "framework": "vllm_tokenizer_patch", "intentId": "37559ea464a347cb9cb0ce0303cee63e", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729150+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dee1fee998c7484c8fc8502182add98a", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729228+00:00", "framework": "vllm_tokenizer_patch", "intentId": "252590bab48d4686b7aa25984b9555bb", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729280+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c20ed6fc934b4d6a8ed84d3007859e83", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729330+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a89899c46c6a4655a33411460043d7fa", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729379+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5de37f6b07f54414b8e14576006b01c7", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729428+00:00", "framework": "vllm-mlu", "intentId": "2e9da52fbb3545fe8bf87050a9d84955", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729486+00:00", "framework": "vllm-mlu", "intentId": "aab586746b1748cca2aa77d45a99ee74", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729536+00:00", "framework": "vllm-mlu", "intentId": "be4ece177c1c4553a2c0e826523c1d53", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729586+00:00", "framework": "vllm-mlu", "intentId": "01c6ffe7f26d4cdc816f002790e11252", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729642+00:00", "framework": "vllm-mlu", "intentId": "8e0cb2dfc12b49148519845e7c195e40", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729698+00:00", "framework": "vllm-mlu", "intentId": "db351721b646460aad8cba837e2be747", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729747+00:00", "framework": "vllm-mlu", "intentId": "fa207239fbd447d7a161dee7d6cbfb48", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729796+00:00", "framework": "vllm-mlu", "intentId": "d71005bf11b74659b705a25c488c6e9b", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729844+00:00", "framework": "vllm-mlu", "intentId": "bc825ec2fc244758be2f1338518fd9d4", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729893+00:00", "framework": "vllm-mlu", "intentId": "5ee43ad686c24133ae38af25fdb7cad7", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729941+00:00", "framework": "vllm-mlu", "intentId": "dfc454e22c54460d83786d187550a446", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729990+00:00", "framework": "vllm-mlu", "intentId": "9869b924c76a4a9bbcc5cdce1608709a", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730045+00:00", "framework": "vllm-mlu", "intentId": "08970f64c4bd425c89f617e6b6b7f889", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730094+00:00", "framework": "vllm-mlu", "intentId": "a4f8f236b05b4e7282ccd0efe357c581", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730142+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c59cf06711a04414add1623394d70af2", "lastModified": "2026-09-14T20:26:18+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "repoId": "prithivMLmods/CEERS-2112-14B-Instruct", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730186+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1d0518377f804123a3eefccd27a6d65a", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730229+00:00", "framework": "vllm_tokenizer_patch", "intentId": "be24060aa10b48199a95e8306e8befe6", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "73f63d2a531b4fa9bb0c107f08b9f6ab", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730334+00:00", "framework": "vllm_tokenizer_patch", "intentId": "02c3e34ba73449a394f8c9139d077a88", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730382+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4700c515afa44bae981e8249631cf0b2", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730430+00:00", "framework": "vllm_tokenizer_patch", "intentId": "35253243ce9b45fb87bfa3cd5553855e", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730477+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c6f1866b35e423a949a4853c2dbced7", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730525+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f6f05917a6ee465fad82168aeb087bf8", "lastModified": "2026-09-15T15:10:12+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730572+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4729980526c04143b389e73947643eba", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730620+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7dfa7d98c3344c4ba5ab8d42f7698232", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730672+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c6866936f0ad4412ba0d25bc970356e7", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730720+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0436f2189e1946acb7e517d7763c9c71", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730774+00:00", "framework": "vllm_tokenizer_patch", "intentId": "729ba3329e574a17b9fdc69c15f08994", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730821+00:00", "framework": "vllm", "intentId": "734a64ed7801408eb4fee72a50da43ef", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730869+00:00", "framework": "vllm", "intentId": "77d21760a0914f12b9b6c6833856deb0", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730916+00:00", "framework": "vllm", "intentId": "c1a593fa6adb4001928fe3c850d0863f", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cba6ee9d56dd41328585bfc90d879ec4", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731002+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1b932900c9534e2289b8e4b198a4168a", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731039+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b5f1c19f56b413881e87c89db5e73c9", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731076+00:00", "framework": "vllm_tokenizer_patch", "intentId": "753964598a924d53a463272809d6e3be", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731113+00:00", "framework": "vllm_tokenizer_patch", "intentId": "733678d8011f40c5a0922d8b5530ce3c", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731150+00:00", "framework": "vllm_tokenizer_patch", "intentId": "548d6c1716364bf98665593c68dfd18c", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731187+00:00", "framework": "vllm_tokenizer_patch", "intentId": "babd096087404d9b969c573c4116b69a", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "17a0d964ac1548ffaf524efa76f10b65", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731268+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cce9fd103e9f41a488a68bb829648112", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731304+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8ef42a478dd742f382c2c85dc5e962fe", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731340+00:00", "framework": "vllm_tokenizer_patch", "intentId": "07657ee787454b7c834286179af1792b", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731377+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b4fb38a23df64dc3806aee3909225e9c", "lastModified": "2026-09-15T15:08:08+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "repoId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731413+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef59cf2affb74d01adfd37051dbe510b", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731449+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a57ee95959a04509986b5b725428832e", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731486+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34b105a9cc694732bb053f74386bcfd5", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731523+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6ffd79b726bf4fa7aa8c26b066e0c354", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731560+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53d725cc2d8e455dabf3a6ababb69c91", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731596+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "acaf365db4334aa2b58a3940704063b5", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731648+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "64e898f71f6c449ca0b6068ef8684ed0", "lastModified": "2026-09-09T13:42:58+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731698+00:00", "framework": "vllm", "intentId": "1da72fda3a184e93965870a154c88742", "lastModified": "2026-08-27T04:11:21+00:00", "modelAddress": "https://modelscope.cn/models/dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "repoId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731754+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a1cdd2096c7f4f5584c810bca42e3fdf", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731797+00:00", "framework": "vllm-patch-tokenizer", "intentId": "cca5d5d30d724b3ca89a8dce8ce7d66f", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731839+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9de68f4e72da4cf68ea7b06e5f9605b2", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731881+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1ddd4d5a27bc490bbb7d66e888d3b7c1", "lastModified": "2026-09-16T16:39:48+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "repoId": "BAAI/RoboBrain2.5-8B-MT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731923+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fdf2e94e3c4b48048a2ddffefd322da9", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731972+00:00", "framework": "vllm-patch-tokenizer", "intentId": "56002a71044e4fd697ade26ffc10ee44", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732014+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e7a317d0d20c4c0cbec9881b9fd34aba", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732055+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1c87487a2a744f39887a5404dea2568e", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732096+00:00", "framework": "vllm-patch-tokenizer", "intentId": "94cc3e8a98bd4b91b2d04bef6b28d42f", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732138+00:00", "framework": "vllm", "intentId": "91270756781b4ce28ea8e28aa8db1c08", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732185+00:00", "framework": "vllm", "intentId": "6f4fd4ed77a24f669b1755e5324fbba4", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732232+00:00", "framework": "vllm", "intentId": "0ef09ec877ff409688342a24ffd8b9e7", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732279+00:00", "framework": "vllm", "intentId": "419a73f8557f426f8daf1d7f831f6b36", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732325+00:00", "framework": "vllm", "intentId": "fa62239fe0534721843e1307ad31cf13", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732372+00:00", "framework": "vllm", "intentId": "0f8a119117da4646bcb0e11b59731a8b", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732419+00:00", "framework": "vllm", "intentId": "6b64673c3ff040f1b2e8b9bea8dc3a13", "lastModified": "2026-09-19T14:48:58+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732471+00:00", "framework": "vllm", "intentId": "78d23ea7bf504b7d8a531a53bd76c2bc", "lastModified": "2026-09-19T14:28:18+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732518+00:00", "framework": "vllm", "intentId": "4b9516b0b780427886379925c1af16c9", "lastModified": "2026-09-19T14:42:49+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732565+00:00", "framework": "vllm", "intentId": "521eabc5935641319aedde9610c94e6a", "lastModified": "2026-09-19T14:43:57+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732611+00:00", "framework": "vllm", "intentId": "78958a3e1aff4591bd052b769be7500a", "lastModified": "2026-09-19T14:37:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732658+00:00", "framework": "vllm", "intentId": "6a72c3f7e35b4cf7b82d118c8c130a3e", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732714+00:00", "framework": "vllm", "intentId": "ed85f7db9c474e6097d7cd07b2b12169", "lastModified": "2026-08-26T18:36:54+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v3-9B", "repoId": "aisingapore/Gemma-SEA-LION-v3-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732760+00:00", "framework": "vllm", "intentId": "06b7b1b374844ae1921cf6b7ad66f191", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732813+00:00", "framework": "vllm", "intentId": "0c6edf70c7074c50b1a471d5d2c5640f", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732860+00:00", "framework": "vllm-customized", "intentId": "11ecbaaa2610441980e9b7a061e57e33", "lastModified": "2026-08-28T13:00:18+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-guardian-4.1-8b", "repoId": "ibm-granite/granite-guardian-4.1-8b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732919+00:00", "framework": "vllm-customized", "intentId": "469f2914335f4faeb4f3d6885676ff68", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732976+00:00", "framework": "vllm", "intentId": "ac60babed6ed4c729fd2c123a47ff886", "lastModified": "2026-08-26T18:43:15+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v2-8B", "repoId": "aisingapore/Llama-SEA-LION-v2-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733033+00:00", "framework": "vllm", "intentId": "a8839df8cb8f4e32bd1309855c3e7ffa", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733077+00:00", "framework": "vllm", "intentId": "d77473eef1914e40be9911efafd3a711", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733119+00:00", "framework": "vllm", "intentId": "3a7eb5dd382448c6b2503e04ef0bfefc", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733161+00:00", "framework": "vllm", "intentId": "b7e930fdc4264b9c9dfe68b97dfbbc5e", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733210+00:00", "framework": "vllm", "intentId": "96f3d547e0654f32b4b6f9b52f0bfc71", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733252+00:00", "framework": "vllm", "intentId": "f8c0f5c001c04b5a95169369d4e06e35", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733301+00:00", "framework": "vllm", "intentId": "9211c77e323e4327ba67227e3c28dcde", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733350+00:00", "framework": "vllm", "intentId": "2038cc45884049c4a4dcfd15cc9bd1b7", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733399+00:00", "framework": "vllm", "intentId": "f6da728a6da546dda4d66eee53eb408f", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733448+00:00", "framework": "vllm", "intentId": "2992708e4be44d6588f11da0a2d04489", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
-{"batchId": "1c4f6c9bd89b46898928018764467782", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733497+00:00", "framework": "vllm", "intentId": "4dd3732c1bc741edb5b3fd7f2c25947b", "lastModified": "2026-09-15T14:57:59+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "repoId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194172+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728716+00:00", "framework": "vllm_tokenizer_patch", "intentId": "857a84b7853e4d5bb04bb032504dbd4d", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194184+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728844+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1c0eafd25e77420982c236f8b5e580dc", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969300", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194187+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a3ff2e6ca8314647889e924ea9c6e25b", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "reason": null, "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194190+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728949+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5b74096d09b49b5b6c798886e516a3e", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194192+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.728999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "82dddaf14d5a426c80cf26e2d14a4664", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969305", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194194+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729048+00:00", "framework": "vllm_tokenizer_patch", "intentId": "37559ea464a347cb9cb0ce0303cee63e", "lastModified": "2026-08-24T20:36:33+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969301", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194196+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729150+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dee1fee998c7484c8fc8502182add98a", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969297", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194198+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729228+00:00", "framework": "vllm_tokenizer_patch", "intentId": "252590bab48d4686b7aa25984b9555bb", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969307", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194200+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729280+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c20ed6fc934b4d6a8ed84d3007859e83", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969302", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194202+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729330+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a89899c46c6a4655a33411460043d7fa", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "reason": null, "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969303", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194203+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729379+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5de37f6b07f54414b8e14576006b01c7", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969299", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194206+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729428+00:00", "framework": "vllm-mlu", "intentId": "2e9da52fbb3545fe8bf87050a9d84955", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969306", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194207+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729486+00:00", "framework": "vllm-mlu", "intentId": "aab586746b1748cca2aa77d45a99ee74", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "reason": null, "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969308", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194210+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729536+00:00", "framework": "vllm-mlu", "intentId": "be4ece177c1c4553a2c0e826523c1d53", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969309", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194212+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729586+00:00", "framework": "vllm-mlu", "intentId": "01c6ffe7f26d4cdc816f002790e11252", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969319", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194214+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729642+00:00", "framework": "vllm-mlu", "intentId": "8e0cb2dfc12b49148519845e7c195e40", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969318", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194215+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729698+00:00", "framework": "vllm-mlu", "intentId": "db351721b646460aad8cba837e2be747", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "reason": null, "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969315", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194217+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729747+00:00", "framework": "vllm-mlu", "intentId": "fa207239fbd447d7a161dee7d6cbfb48", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969312", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194220+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729796+00:00", "framework": "vllm-mlu", "intentId": "d71005bf11b74659b705a25c488c6e9b", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969313", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194222+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729844+00:00", "framework": "vllm-mlu", "intentId": "bc825ec2fc244758be2f1338518fd9d4", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "reason": null, "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969310", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194224+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729893+00:00", "framework": "vllm-mlu", "intentId": "5ee43ad686c24133ae38af25fdb7cad7", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969314", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194226+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729941+00:00", "framework": "vllm-mlu", "intentId": "dfc454e22c54460d83786d187550a446", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969316", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194228+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.729990+00:00", "framework": "vllm-mlu", "intentId": "9869b924c76a4a9bbcc5cdce1608709a", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "reason": null, "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969311", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194230+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730045+00:00", "framework": "vllm-mlu", "intentId": "08970f64c4bd425c89f617e6b6b7f889", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969317", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194232+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730094+00:00", "framework": "vllm-mlu", "intentId": "a4f8f236b05b4e7282ccd0efe357c581", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "reason": null, "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194234+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730142+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c59cf06711a04414add1623394d70af2", "lastModified": "2026-09-14T20:26:18+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "reason": null, "repoId": "prithivMLmods/CEERS-2112-14B-Instruct", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969325", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194236+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730186+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1d0518377f804123a3eefccd27a6d65a", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969323", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194238+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730229+00:00", "framework": "vllm_tokenizer_patch", "intentId": "be24060aa10b48199a95e8306e8befe6", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "reason": null, "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969322", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194240+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "73f63d2a531b4fa9bb0c107f08b9f6ab", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "reason": null, "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969324", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194241+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730334+00:00", "framework": "vllm_tokenizer_patch", "intentId": "02c3e34ba73449a394f8c9139d077a88", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "reason": null, "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969320", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194243+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730382+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4700c515afa44bae981e8249631cf0b2", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "reason": null, "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969326", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194245+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730430+00:00", "framework": "vllm_tokenizer_patch", "intentId": "35253243ce9b45fb87bfa3cd5553855e", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "reason": null, "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969330", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194247+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730477+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c6f1866b35e423a949a4853c2dbced7", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "reason": null, "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969328", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194249+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730525+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f6f05917a6ee465fad82168aeb087bf8", "lastModified": "2026-09-15T15:10:12+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "reason": null, "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969329", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194251+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730572+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4729980526c04143b389e73947643eba", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "reason": null, "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969327", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194253+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730620+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7dfa7d98c3344c4ba5ab8d42f7698232", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "reason": null, "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969331", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194255+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730672+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c6866936f0ad4412ba0d25bc970356e7", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "reason": null, "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969332", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194257+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730720+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0436f2189e1946acb7e517d7763c9c71", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "reason": null, "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194259+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730774+00:00", "framework": "vllm_tokenizer_patch", "intentId": "729ba3329e574a17b9fdc69c15f08994", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "reason": null, "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969333", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194260+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730821+00:00", "framework": "vllm", "intentId": "734a64ed7801408eb4fee72a50da43ef", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "reason": null, "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969337", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194262+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730869+00:00", "framework": "vllm", "intentId": "77d21760a0914f12b9b6c6833856deb0", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969336", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194264+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730916+00:00", "framework": "vllm", "intentId": "c1a593fa6adb4001928fe3c850d0863f", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969334", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194266+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.730962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cba6ee9d56dd41328585bfc90d879ec4", "lastModified": "2026-09-14T13:40:21+00:00", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "reason": null, "repoId": "IntervitensInc/kek_mk3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969341", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194268+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731002+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1b932900c9534e2289b8e4b198a4168a", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "reason": null, "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969340", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194270+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731039+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b5f1c19f56b413881e87c89db5e73c9", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "reason": null, "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969342", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194272+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731076+00:00", "framework": "vllm_tokenizer_patch", "intentId": "753964598a924d53a463272809d6e3be", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969339", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194273+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731113+00:00", "framework": "vllm_tokenizer_patch", "intentId": "733678d8011f40c5a0922d8b5530ce3c", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "reason": null, "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969338", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194275+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731150+00:00", "framework": "vllm_tokenizer_patch", "intentId": "548d6c1716364bf98665593c68dfd18c", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969343", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194277+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731187+00:00", "framework": "vllm_tokenizer_patch", "intentId": "babd096087404d9b969c573c4116b69a", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969346", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194279+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731230+00:00", "framework": "vllm_tokenizer_patch", "intentId": "17a0d964ac1548ffaf524efa76f10b65", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969348", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194281+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731268+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cce9fd103e9f41a488a68bb829648112", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969347", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194282+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731304+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8ef42a478dd742f382c2c85dc5e962fe", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969345", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194284+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731340+00:00", "framework": "vllm_tokenizer_patch", "intentId": "07657ee787454b7c834286179af1792b", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969349", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194286+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731377+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b4fb38a23df64dc3806aee3909225e9c", "lastModified": "2026-09-15T15:08:08+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "reason": null, "repoId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969344", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194288+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731413+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ef59cf2affb74d01adfd37051dbe510b", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969350", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194290+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731449+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a57ee95959a04509986b5b725428832e", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969357", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194292+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731486+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34b105a9cc694732bb053f74386bcfd5", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969351", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194294+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731523+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6ffd79b726bf4fa7aa8c26b066e0c354", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969360", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194296+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731560+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53d725cc2d8e455dabf3a6ababb69c91", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4969352", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194298+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731596+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "acaf365db4334aa2b58a3940704063b5", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969355", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194300+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731648+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "64e898f71f6c449ca0b6068ef8684ed0", "lastModified": "2026-09-09T13:42:58+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "reason": null, "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194302+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731698+00:00", "framework": "vllm", "intentId": "1da72fda3a184e93965870a154c88742", "lastModified": "2026-08-27T04:11:21+00:00", "modelAddress": "https://modelscope.cn/models/dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "reason": null, "repoId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194304+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731754+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a1cdd2096c7f4f5584c810bca42e3fdf", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "reason": null, "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969353", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194306+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731797+00:00", "framework": "vllm-patch-tokenizer", "intentId": "cca5d5d30d724b3ca89a8dce8ce7d66f", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969354", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194308+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731839+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9de68f4e72da4cf68ea7b06e5f9605b2", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "reason": null, "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969356", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194310+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731881+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1ddd4d5a27bc490bbb7d66e888d3b7c1", "lastModified": "2026-09-16T16:39:48+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-MT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969358", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194312+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731923+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fdf2e94e3c4b48048a2ddffefd322da9", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "reason": null, "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969362", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194313+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.731972+00:00", "framework": "vllm-patch-tokenizer", "intentId": "56002a71044e4fd697ade26ffc10ee44", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969363", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194315+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732014+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e7a317d0d20c4c0cbec9881b9fd34aba", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194317+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732055+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1c87487a2a744f39887a5404dea2568e", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "reason": null, "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969367", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194319+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732096+00:00", "framework": "vllm-patch-tokenizer", "intentId": "94cc3e8a98bd4b91b2d04bef6b28d42f", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969365", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194321+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732138+00:00", "framework": "vllm", "intentId": "91270756781b4ce28ea8e28aa8db1c08", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "reason": null, "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969373", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194322+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732185+00:00", "framework": "vllm", "intentId": "6f4fd4ed77a24f669b1755e5324fbba4", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "reason": null, "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969366", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194324+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732232+00:00", "framework": "vllm", "intentId": "0ef09ec877ff409688342a24ffd8b9e7", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "reason": null, "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194326+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732279+00:00", "framework": "vllm", "intentId": "419a73f8557f426f8daf1d7f831f6b36", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "reason": null, "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969368", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194328+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732325+00:00", "framework": "vllm", "intentId": "fa62239fe0534721843e1307ad31cf13", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969370", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194330+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732372+00:00", "framework": "vllm", "intentId": "0f8a119117da4646bcb0e11b59731a8b", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969371", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194332+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732419+00:00", "framework": "vllm", "intentId": "6b64673c3ff040f1b2e8b9bea8dc3a13", "lastModified": "2026-09-19T14:48:58+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969369", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194334+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732471+00:00", "framework": "vllm", "intentId": "78d23ea7bf504b7d8a531a53bd76c2bc", "lastModified": "2026-09-19T14:28:18+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969378", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194336+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732518+00:00", "framework": "vllm", "intentId": "4b9516b0b780427886379925c1af16c9", "lastModified": "2026-09-19T14:42:49+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969374", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194338+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732565+00:00", "framework": "vllm", "intentId": "521eabc5935641319aedde9610c94e6a", "lastModified": "2026-09-19T14:43:57+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969377", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194340+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732611+00:00", "framework": "vllm", "intentId": "78958a3e1aff4591bd052b769be7500a", "lastModified": "2026-09-19T14:37:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969379", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194342+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732658+00:00", "framework": "vllm", "intentId": "6a72c3f7e35b4cf7b82d118c8c130a3e", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "reason": null, "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969375", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194343+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732714+00:00", "framework": "vllm", "intentId": "ed85f7db9c474e6097d7cd07b2b12169", "lastModified": "2026-08-26T18:36:54+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v3-9B", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v3-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969376", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194345+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732760+00:00", "framework": "vllm", "intentId": "06b7b1b374844ae1921cf6b7ad66f191", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "reason": null, "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969385", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194347+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732813+00:00", "framework": "vllm", "intentId": "0c6edf70c7074c50b1a471d5d2c5640f", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "reason": null, "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969381", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194349+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732860+00:00", "framework": "vllm-customized", "intentId": "11ecbaaa2610441980e9b7a061e57e33", "lastModified": "2026-08-28T13:00:18+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-guardian-4.1-8b", "reason": null, "repoId": "ibm-granite/granite-guardian-4.1-8b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969382", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194351+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732919+00:00", "framework": "vllm-customized", "intentId": "469f2914335f4faeb4f3d6885676ff68", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969380", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194353+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.732976+00:00", "framework": "vllm", "intentId": "ac60babed6ed4c729fd2c123a47ff886", "lastModified": "2026-08-26T18:43:15+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v2-8B", "reason": null, "repoId": "aisingapore/Llama-SEA-LION-v2-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "4969384", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194355+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733033+00:00", "framework": "vllm", "intentId": "a8839df8cb8f4e32bd1309855c3e7ffa", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "reason": null, "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969383", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194357+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733077+00:00", "framework": "vllm", "intentId": "d77473eef1914e40be9911efafd3a711", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "reason": null, "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969387", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194359+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733119+00:00", "framework": "vllm", "intentId": "3a7eb5dd382448c6b2503e04ef0bfefc", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "reason": null, "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969389", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194360+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733161+00:00", "framework": "vllm", "intentId": "b7e930fdc4264b9c9dfe68b97dfbbc5e", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "reason": null, "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969388", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194362+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733210+00:00", "framework": "vllm", "intentId": "96f3d547e0654f32b4b6f9b52f0bfc71", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "reason": null, "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4969390", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194364+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733252+00:00", "framework": "vllm", "intentId": "f8c0f5c001c04b5a95169369d4e06e35", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "reason": null, "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194366+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733301+00:00", "framework": "vllm", "intentId": "9211c77e323e4327ba67227e3c28dcde", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "reason": null, "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194367+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733350+00:00", "framework": "vllm", "intentId": "2038cc45884049c4a4dcfd15cc9bd1b7", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "reason": null, "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969395", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194369+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733399+00:00", "framework": "vllm", "intentId": "f6da728a6da546dda4d66eee53eb408f", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "reason": null, "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969392", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194371+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733448+00:00", "framework": "vllm", "intentId": "2992708e4be44d6588f11da0a2d04489", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "reason": null, "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969394", "taskType": "text-generation"}
+{"batchId": "1c4f6c9bd89b46898928018764467782", "completedAt": "2026-09-20T03:09:19.194374+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:09:10.733497+00:00", "framework": "vllm", "intentId": "4dd3732c1bc741edb5b3fd7f2c25947b", "lastModified": "2026-09-15T14:57:59+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "reason": null, "repoId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969393", "taskType": "text-generation"}
 {"batchId": "a0638aa6b9d441fc8127d1ff98b0380e", "completedAt": "2026-09-20T02:22:36.529135+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-10T13:27:22.633245+00:00", "framework": "vllm", "intentId": "8986a9476a034876a874432fe981a93c", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "success", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation"}
 {"batchId": "3601d2529e2f4dbab4abc91721a031a6", "completedAt": "2026-09-20T01:08:42.115049+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-19T12:27:15.291074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "56909ec2a21e4e3f9e0a55deb70d46c0", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "taskType": "text-generation"}
 {"batchId": "17f9bc75c9254b23a97517096a945dfd", "completedAt": "2026-09-20T00:27:18.357432+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-09T17:53:27.791335+00:00", "framework": "vllm-mlu", "intentId": "e8b41bd8a15a4f4ab9051c3e998dfc85", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "success", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index d59145ed54..8d2a07311c 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,38 +1,40 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 1199
+    "unified_success_first": 1299
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 17,
-    "text-generation|Ascend_910-b3|vllm": 22,
-    "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 64,
+    "text-generation|Ascend_910-b3|vllm": 25,
+    "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 81,
     "text-generation|Ascend_910-b4|llamacpp": 13,
-    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 78,
-    "text-generation|Biren_166m|vllm": 61,
+    "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 89,
+    "text-generation|Biren_166m|vllm": 62,
     "text-generation|Biren_166m|vllm_fix_tokenizer": 13,
-    "text-generation|Cambricon_mlu-370-x4|vllm": 10,
-    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 55,
+    "text-generation|Cambricon_mlu-370-x4|vllm": 25,
+    "text-generation|Cambricon_mlu-370-x4|vllm-customized": 1,
+    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 69,
     "text-generation|Cambricon_mlu-370-x8|vllm": 14,
-    "text-generation|Cambricon_mlu-370-x8|vllm-customized": 10,
+    "text-generation|Cambricon_mlu-370-x8|vllm-customized": 11,
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 78,
     "text-generation|Iluvatar_bi-150|llamacpp": 16,
-    "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 81,
+    "text-generation|Iluvatar_bi-150|vllm": 6,
+    "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 83,
     "text-generation|Iluvatar_mrv-100|vllm": 57,
     "text-generation|Kunlunxin_p-800|vllm": 1,
-    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 131,
-    "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 8,
+    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 133,
+    "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 20,
     "text-generation|MetaX_c-500|vllm": 100,
     "text-generation|Mthreads_s4000|llamacpp": 17,
-    "text-generation|Mthreads_s4000|vllm": 84,
+    "text-generation|Mthreads_s4000|vllm": 85,
     "text-generation|Sunrise_pt-200-x1|vllm": 62,
     "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 62,
     "text-generation|Vastai_va16|vllm_fix_tokenizer": 52,
     "text-generation|hygon_k100-ai|llamacpp": 18,
-    "text-generation|hygon_k100-ai|vllm": 4,
-    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 71
+    "text-generation|hygon_k100-ai|vllm": 9,
+    "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 80
   },
-  "acceptedSinceRefresh": 1199,
-  "acceptedTotal": 1199,
-  "generatedAt": "2026-09-20T02:52:52.388462+00:00",
+  "acceptedSinceRefresh": 1299,
+  "acceptedTotal": 1299,
+  "generatedAt": "2026-09-20T03:09:19.156982+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 4dd515b17a..4a7ff67b63 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -785,3 +785,103 @@
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-19T12:27:16.554034+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
 {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-19T17:00:42.497473+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4960599", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
 {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-19T17:18:17.894388+00:00", "targetGpu": "Biren_166m", "taskId": "4960871", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "submitTime": "2026-09-20T03:09:11.490200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:09:11.539809+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969300", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "submitTime": "2026-09-20T03:09:11.548946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-20T03:09:11.553586+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969305", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "submitTime": "2026-09-20T03:09:11.542224+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969301", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:09:11.536035+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T03:09:11.551543+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969307", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:09:11.543885+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969302", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T03:09:11.537727+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969303", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-20T03:09:11.545717+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969299", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-20T03:09:11.547157+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969306", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "submitTime": "2026-09-20T03:09:17.666037+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969308", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-20T03:09:17.669721+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969309", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:09:17.737602+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969319", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-20T03:09:17.700645+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969318", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "submitTime": "2026-09-20T03:09:17.689869+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969315", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "submitTime": "2026-09-20T03:09:17.671625+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969312", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-20T03:09:17.686580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-20T03:09:17.678712+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969310", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T03:09:17.684662+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:09:17.691818+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969316", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "modelId": "pfnet/plamo-3-nict-8b-base", "submitTime": "2026-09-20T03:09:17.681306+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969311", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T03:09:17.694934+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969317", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/prithivMLmods/CEERS-2112-14B-Instruct", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "submitTime": "2026-09-20T03:09:17.845020+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "modelId": "BAAI/RoboBrain2.5-8B-NV", "submitTime": "2026-09-20T03:09:17.837872+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969323", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-20T03:09:17.795054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969322", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-20T03:09:17.849368+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969324", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "submitTime": "2026-09-20T03:09:17.835766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969320", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "submitTime": "2026-09-20T03:09:17.880383+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969326", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-20T03:09:17.942242+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969330", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "submitTime": "2026-09-20T03:09:17.940876+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969328", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "submitTime": "2026-09-20T03:09:17.939093+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969329", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "submitTime": "2026-09-20T03:09:17.944560+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969327", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-20T03:09:17.951764+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969331", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "submitTime": "2026-09-20T03:09:17.986096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969332", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T03:09:18.037481+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-20T03:09:18.046569+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969333", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-20T03:09:18.038960+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969337", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:09:18.043058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969336", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:09:18.040317+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969334", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/IntervitensInc/kek_mk3", "modelId": "IntervitensInc/kek_mk3", "submitTime": "2026-09-20T03:09:18.153275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969341", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "submitTime": "2026-09-20T03:09:18.145895+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969340", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-20T03:09:18.139946+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969342", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T03:09:18.136303+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969339", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "submitTime": "2026-09-20T03:09:18.141281+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969338", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-20T03:09:18.150831+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969343", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T03:09:18.240937+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969346", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-20T03:09:18.249136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969348", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T03:09:18.253824+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969347", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-20T03:09:18.246521+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969345", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "submitTime": "2026-09-20T03:09:18.252481+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969349", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-20T03:09:18.238662+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969344", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-20T03:09:18.334506+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969350", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "submitTime": "2026-09-20T03:09:18.445246+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969357", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "submitTime": "2026-09-20T03:09:18.346394+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969351", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "submitTime": "2026-09-20T03:09:18.384232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969360", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-20T03:09:18.376994+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969352", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
+{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "submitTime": "2026-09-20T03:09:18.382878+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969355", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
+{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T03:09:18.452113+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-20T03:09:18.437418+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969353", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T03:09:18.435716+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969354", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-20T03:09:18.447188+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969356", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T03:09:18.449082+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969358", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "submitTime": "2026-09-20T03:09:18.543315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969362", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T03:09:18.549276+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969363", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "submitTime": "2026-09-20T03:09:18.638557+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969367", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "submitTime": "2026-09-20T03:09:18.636450+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969365", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-20T03:09:18.688571+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969373", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-20T03:09:18.640110+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969366", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "submitTime": "2026-09-20T03:09:18.738031+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-20T03:09:18.670958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969368", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "submitTime": "2026-09-20T03:09:18.682889+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969370", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T03:09:18.680650+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969371", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-20T03:09:18.686887+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969369", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-20T03:09:18.793172+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969378", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-20T03:09:18.791323+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969374", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T03:09:18.838488+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969377", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T03:09:18.836648+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969379", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T03:09:18.840393+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969375", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v3-9B", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "submitTime": "2026-09-20T03:09:18.835980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969376", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-20T03:09:18.943995+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969385", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "submitTime": "2026-09-20T03:09:18.882740+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969381", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
+{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-guardian-4.1-8b", "modelId": "ibm-granite/granite-guardian-4.1-8b", "submitTime": "2026-09-20T03:09:18.880160+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969382", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
+{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T03:09:18.890535+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969380", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x4"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v2-8B", "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "submitTime": "2026-09-20T03:09:18.938123+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969384", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-20T03:09:18.939756+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969383", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "modelId": "XHToken/Spark-X2.5-4B", "submitTime": "2026-09-20T03:09:19.041224+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969387", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "modelId": "XHToken/Spark-X2.5-1.7B", "submitTime": "2026-09-20T03:09:19.037544+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969389", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-20T03:09:18.999314+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969388", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T03:09:19.035946+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969390", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-20T03:09:19.045622+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-20T03:09:18.989339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "submitTime": "2026-09-20T03:09:19.100832+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969395", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-20T03:09:19.090425+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969392", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-20T03:09:19.091891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969394", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "submitTime": "2026-09-20T03:09:19.097857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969393", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-bi-150"}
diff --git a/manifest.json b/manifest.json
index fd57b7e563..39df951904 100644
--- a/manifest.json
+++ b/manifest.json
@@ -9,16 +9,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe",
     ".modelhub_state/recent_outcomes.jsonl": "7e47e1c5283224980b4180e88470bce5b10b60c22a36a05350a29692eeb20732",
     ".modelhub_state/recovery_active_tasks.jsonl": "01c0792c4412947a4efe87bbe81c102f23e0c6a5686b237838267599c64f2760",
-    ".modelhub_state/recovery_intents.jsonl": "48d4411323b02491305ded00f571b45a24252504f1dd99e68d94ebb774ef0628",
-    ".modelhub_state/routing_intelligence.json": "8c20bc7384b33a8e1f03e0e5d4c988fcf150eed7edd6a5c91e56a4e5585a0308",
+    ".modelhub_state/recovery_intents.jsonl": "09718df1ca497bed60ccbdf269ce049e20bdc9a79cd6a4b331111e875a669343",
+    ".modelhub_state/routing_intelligence.json": "66eb17cab788174e5669456ef4f53004b423cab74b0996f4f8c118b21c73d905",
     ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
-    "ledger/submissions.jsonl": "48cfe94eecef4ebdb37e66ca7d4c2038a1fc30cc47d9c845813f135d0c5fef71",
-    "outcomes/submissions.jsonl": "6efc3fd5d012d6413926d8b714c582a289d8152947378d6bdd3a9c9e841446ab"
+    "ledger/submissions.jsonl": "a3c0f026a8b34c0ffc89a74964506afb220ef5bdd8001f5488d5212e98b60aec",
+    "outcomes/submissions.jsonl": "cf8ccf0b97512fd4a227eec49d5918f2e0009264d41105871ad1609a0f7f7ba0"
   },
-  "generation": 10108,
-  "phase": "intent",
+  "generation": 10109,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-20T03:09:10.851554+00:00",
+  "updatedAt": "2026-09-20T03:09:19.272939+00:00",
   "writerId": "f67e4ec113c04968a9d9484fb8e36bd4"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index 5550407b78..222363935b 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -588,3 +588,103 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ysqlian/YZH_Model", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6171927000, "estimatedRequiredGiB": 6.915, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 6187845052, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3085938688, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen2", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6187845052}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:52.308078+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969092", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:52.295134+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969090", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ibm-granite/granite-guardian-4.1-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16761144464, "estimatedRequiredGiB": 18.743, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 16770924251, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8380551168, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:granite", "custom_tag:guardian", "custom_tag:safety", "custom_tag:hallucination"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16770924251}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:52.310071+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969093", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.490200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.539809+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969300", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.548946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.553586+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969305", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.542224+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969301", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.536035+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969297", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.551543+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969307", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443052}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.543885+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969302", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.537727+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969303", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.545717+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969299", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:11.547157+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969306", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.666037+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969308", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.669721+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969309", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.737602+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969319", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.700645+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969318", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.689869+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969315", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.671625+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969312", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.686580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969313", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.678712+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969310", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.684662+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969314", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.691818+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969316", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.681306+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969311", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.694934+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969317", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.845020+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969325", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.837872+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969323", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.795054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969322", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.849368+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969324", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24651300904, "estimatedRequiredGiB": 27.587, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24684544516, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 24684544516}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.835766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969320", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.880383+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969326", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.942242+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969330", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.940876+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969328", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.939093+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969329", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.944560+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969327", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.951764+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969331", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:17.986096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969332", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.037481+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.046569+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969333", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.038960+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969337", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.043058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969336", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.040317+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969334", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.153275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969341", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.145895+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969340", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.139946+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969342", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.136303+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969339", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.141281+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969338", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.150831+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969343", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.240937+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969346", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.249136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969348", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.253824+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969347", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.246521+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969345", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.252481+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969349", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.238662+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969344", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16314185171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.334506+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969350", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.445246+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969357", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.346394+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969351", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.384232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969360", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.376994+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969352", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.382878+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969355", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.452113+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.437418+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969353", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.435716+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969354", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.447188+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969356", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.449082+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969358", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.543315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969362", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.549276+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969363", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.638557+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969367", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.636450+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969365", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.688571+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969373", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.640110+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969366", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.738031+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.670958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969368", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.682889+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969370", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.680650+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969371", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.686887+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969369", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.793172+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969378", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.791323+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969374", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.838488+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969377", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.836648+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969379", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.840393+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969375", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.835980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969376", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.943995+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969385", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.882740+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969381", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "ibm-granite/granite-guardian-4.1-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16761144464, "estimatedRequiredGiB": 18.743, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 16770924251, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8380551168, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:granite", "custom_tag:guardian", "custom_tag:safety", "custom_tag:hallucination"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16770924251}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.880160+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969382", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.890535+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969380", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Llama-SEA-LION-v2-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.961, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16071447395, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16071447395}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.938123+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969384", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.939756+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969383", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.041224+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969387", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.037544+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969389", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.999314+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969388", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.035946+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969390", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.045622+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.989339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22210552448, "estimatedRequiredGiB": 24.849, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22234091413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 17463440388, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:blackwell", "custom_tag:a100"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 22234091413}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.100832+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969395", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.090425+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969392", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.091891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969394", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:19.097857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969393", "taskType": "text-generation", "verifyResult": null}