From 24d872fc5e01c3702f2fb44d13d7913a92f0094f Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 02:05:57 +0000 Subject: [PATCH] state: generation 11073 (result) --- .modelhub_state/recovery_intents.jsonl | 106 ++++++++-------------- .modelhub_state/routing_intelligence.json | 12 +-- ledger/submissions.jsonl | 2 + manifest.json | 14 +-- outcomes/submissions.jsonl | 2 + 5 files changed, 53 insertions(+), 83 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 51bed65c49..78a2342f41 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1896,42 +1896,42 @@ {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484388+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.658135+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e0544b98abbd4b32a7296b3da8f25f25", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "reason": null, "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4991516", "taskType": "text-generation"} {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484427+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.658557+00:00", "framework": "vllm_fix_tokenizer", "intentId": "da8eddd6c65344d592de0f00f25f064f", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation"} {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484539+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.660134+00:00", "framework": "vllm_fix_tokenizer", "intentId": "930b9d858b7840ccb12c3753fcb0f7b1", "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": "Biren_166m", "taskId": "4991645", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.295876+00:00", "framework": "vllm", "intentId": "0ad4249dfa4f41f2b2e642c60aea1d53", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.295997+00:00", "framework": "vllm", "intentId": "f914aa78926b479c9ee751ec1563929d", "lastModified": "2026-08-24T20:01:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296051+00:00", "framework": "vllm", "intentId": "ca718e474c59477aaedb0af9640c3b1e", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296101+00:00", "framework": "vllm-customized", "intentId": "70955155729c4e4bad886437bc411e89", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296172+00:00", "framework": "vllm-customized", "intentId": "fc2edbecc97b42c98c2f093e69d3066c", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296244+00:00", "framework": "vllm-customized", "intentId": "05fe25ec5a2849518b814e98ffa00cf1", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296304+00:00", "framework": "vllm-customized", "intentId": "9c7c08f838bf45a1b9d41348ee985dfd", "lastModified": "2026-08-24T19:40:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296363+00:00", "framework": "vllm-customized", "intentId": "806363edd0b6459dbf9efe772d09bfcb", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296423+00:00", "framework": "vllm-customized", "intentId": "82c1597cf46f48ebb8a1462830d12ffa", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296495+00:00", "framework": "vllm-customized", "intentId": "39d7c495aa6345148a84e587dd587a5b", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296554+00:00", "framework": "vllm-customized", "intentId": "afdc42a0629b45db9932690d5e8ba636", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296613+00:00", "framework": "vllm-customized", "intentId": "2762e640ea364301a5249ea9a5ab109c", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296709+00:00", "framework": "vllm-customized", "intentId": "6dc4394a0243419fa26dcbab4763c39d", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296770+00:00", "framework": "vllm-customized", "intentId": "ec05bab088ff4407b6e0f36ecfbc8fe1", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296829+00:00", "framework": "vllm-customized", "intentId": "03614dbe1e1b44dc8834b7fe35cc6e39", "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": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296889+00:00", "framework": "vllm", "intentId": "d57f041fc0214471a109d9bbb7d84a06", "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": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296933+00:00", "framework": "vllm", "intentId": "b7d279748a424512b0948c1ee2a477dc", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296976+00:00", "framework": "vllm", "intentId": "c25b4eed3f3f4ca3a8a4c633df50997a", "lastModified": "2026-08-24T20:26:05+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297019+00:00", "framework": "vllm", "intentId": "2845d2a06dc6404ea49f5b2fbc83bfea", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297071+00:00", "framework": "vllm", "intentId": "7c8afd91b7ed491b8e0ada0e6af4cc92", "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": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297122+00:00", "framework": "vllm", "intentId": "e1b71dd8d3004fc9a862dc4b2076a5ba", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297165+00:00", "framework": "vllm", "intentId": "f94cd50ee5854be4b60fc4395142460d", "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": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297207+00:00", "framework": "vllm", "intentId": "22f3b7477f4547ba9fc10a8a4a9424a7", "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": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297250+00:00", "framework": "vllm", "intentId": "2ce5b9e6dba344a48e23925fc6b08e41", "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": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297291+00:00", "framework": "vllm", "intentId": "ef279f16a68148329d5a1bc3ba6c03ac", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297352+00:00", "framework": "vllm", "intentId": "0da6e908a19b4c2d8419a7fee6d8d768", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297411+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3ddc8b19f4940e28db3767d265c0787", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297467+00:00", "framework": "vllm_fix_tokenizer", "intentId": "33181794380d414cae6f86b270e86a03", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297540+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8c09dd6bae984a499812969befabb837", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297605+00:00", "framework": "vllm_fix_tokenizer", "intentId": "848bb95a161d4e9c85992141e6083400", "lastModified": "2026-09-10T05:34:35+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "99d8f84a0aef4f988d4c4577d97a2252", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e34987bdbd9141bb8c09f8fcb39793bd", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297811+00:00", "framework": "vllm_fix_tokenizer", "intentId": "567bedd90430404a9f352d557f43f72f", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297878+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bdbccba9f76940618c97c1152046d964", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297948+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34a995aa9d1f41e69f78aa53e635f0ab", "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": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.298003+00:00", "framework": "vllm_fix_tokenizer", "intentId": "140badcde699403f8b8cd92abbd1d1d5", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763830+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296829+00:00", "framework": "vllm-customized", "intentId": "03614dbe1e1b44dc8834b7fe35cc6e39", "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": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763903+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297811+00:00", "framework": "vllm_fix_tokenizer", "intentId": "567bedd90430404a9f352d557f43f72f", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763915+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.298003+00:00", "framework": "vllm_fix_tokenizer", "intentId": "140badcde699403f8b8cd92abbd1d1d5", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763911+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297948+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34a995aa9d1f41e69f78aa53e635f0ab", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763907+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297878+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bdbccba9f76940618c97c1152046d964", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763899+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e34987bdbd9141bb8c09f8fcb39793bd", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763895+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297660+00:00", "framework": "vllm_fix_tokenizer", "intentId": "99d8f84a0aef4f988d4c4577d97a2252", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763891+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297605+00:00", "framework": "vllm_fix_tokenizer", "intentId": "848bb95a161d4e9c85992141e6083400", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763887+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297540+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8c09dd6bae984a499812969befabb837", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763883+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297467+00:00", "framework": "vllm_fix_tokenizer", "intentId": "33181794380d414cae6f86b270e86a03", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763879+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297411+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3ddc8b19f4940e28db3767d265c0787", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763874+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297352+00:00", "framework": "vllm", "intentId": "0da6e908a19b4c2d8419a7fee6d8d768", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763870+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297291+00:00", "framework": "vllm", "intentId": "ef279f16a68148329d5a1bc3ba6c03ac", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763866+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297250+00:00", "framework": "vllm", "intentId": "2ce5b9e6dba344a48e23925fc6b08e41", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763862+00:00", "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297207+00:00", "framework": "vllm", "intentId": "22f3b7477f4547ba9fc10a8a4a9424a7", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763858+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297165+00:00", "framework": "vllm", "intentId": "f94cd50ee5854be4b60fc4395142460d", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763854+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297122+00:00", "framework": "vllm", "intentId": "e1b71dd8d3004fc9a862dc4b2076a5ba", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763850+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297071+00:00", "framework": "vllm", "intentId": "7c8afd91b7ed491b8e0ada0e6af4cc92", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763845+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.297019+00:00", "framework": "vllm", "intentId": "2845d2a06dc6404ea49f5b2fbc83bfea", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763842+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296976+00:00", "framework": "vllm", "intentId": "c25b4eed3f3f4ca3a8a4c633df50997a", "repoId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763838+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296933+00:00", "framework": "vllm", "intentId": "b7d279748a424512b0948c1ee2a477dc", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763834+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296889+00:00", "framework": "vllm", "intentId": "d57f041fc0214471a109d9bbb7d84a06", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763825+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296770+00:00", "framework": "vllm-customized", "intentId": "ec05bab088ff4407b6e0f36ecfbc8fe1", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763822+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296709+00:00", "framework": "vllm-customized", "intentId": "6dc4394a0243419fa26dcbab4763c39d", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763817+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296613+00:00", "framework": "vllm-customized", "intentId": "2762e640ea364301a5249ea9a5ab109c", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763813+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296554+00:00", "framework": "vllm-customized", "intentId": "afdc42a0629b45db9932690d5e8ba636", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763809+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296495+00:00", "framework": "vllm-customized", "intentId": "39d7c495aa6345148a84e587dd587a5b", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763805+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296423+00:00", "framework": "vllm-customized", "intentId": "82c1597cf46f48ebb8a1462830d12ffa", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763801+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296363+00:00", "framework": "vllm-customized", "intentId": "806363edd0b6459dbf9efe772d09bfcb", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763798+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296304+00:00", "framework": "vllm-customized", "intentId": "9c7c08f838bf45a1b9d41348ee985dfd", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763795+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296244+00:00", "framework": "vllm-customized", "intentId": "05fe25ec5a2849518b814e98ffa00cf1", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763792+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296172+00:00", "framework": "vllm-customized", "intentId": "fc2edbecc97b42c98c2f093e69d3066c", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763788+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296101+00:00", "framework": "vllm-customized", "intentId": "70955155729c4e4bad886437bc411e89", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763784+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.296051+00:00", "framework": "vllm", "intentId": "ca718e474c59477aaedb0af9640c3b1e", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763779+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.295997+00:00", "framework": "vllm", "intentId": "f914aa78926b479c9ee751ec1563929d", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "8fa18999f8184b0f93a54054ba0b490e", "completedAt": "2026-09-21T02:05:57.763750+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:01:42.295876+00:00", "framework": "vllm", "intentId": "0ad4249dfa4f41f2b2e642c60aea1d53", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484589+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.660938+00:00", "framework": "vllm", "intentId": "73480e8e973647b5a7ec9727c6c1f81d", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484586+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.660890+00:00", "framework": "vllm", "intentId": "7e9098c490da44d7bda31ef58b12e538", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "cb345195717f4cd8ad228abbd9cc33ce", "completedAt": "2026-09-21T02:01:41.484584+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:54:15.660842+00:00", "framework": "vllm", "intentId": "e4f98335b23143359c8c4f9a188d2954", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} @@ -2198,37 +2198,3 @@ {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117410+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736893+00:00", "framework": "vllm", "intentId": "5900b6da1ef44bdebc555ea4ad037950", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117407+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736846+00:00", "framework": "vllm", "intentId": "194d974a154446358b1fda0c440dd6e8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117405+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736798+00:00", "framework": "vllm", "intentId": "ccb31c440fc84ce2a28f0bba9fada351", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117402+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736750+00:00", "framework": "vllm", "intentId": "bf2c6591046a462f836e1cd25d98fe73", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117399+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736701+00:00", "framework": "vllm", "intentId": "93233ee2b6e945b3be73ca7755e45d82", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117396+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736654+00:00", "framework": "vllm-patch-tokenizer", "intentId": "f47a9516503541e581c855a0e21617d9", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117393+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2035e12bf4bb4179985e56fd10d59249", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117390+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34d173e59db24680a68d3a177668c80f", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117388+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4607201015384e039b0f75ff91584eab", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117386+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736483+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a9b4f3250a0a4e5e812f3dd3f6c1913f", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117383+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736441+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a060610a7737468b9c44d40d712b575e", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117380+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736399+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a7eed7219db46e69c61c9be724a6343", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117377+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736350+00:00", "framework": "vllm", "intentId": "00a0c8773b3646be9f4e1cc011c4cac9", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117374+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736307+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ab9dce96b5bf440794922595dc34c3f5", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117371+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736264+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cb0e3df69bc44fc2a273a138d58e45a1", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117368+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736222+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a35acfe3c8344574aee8e7624b0bb0e0", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117366+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736180+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7876960e4fae45d9a7db3b1cee683695", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117362+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "451e4445478548fd89a971b588d6dada", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117359+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736095+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6136c597502f4af5af517020f6f4d3db", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117356+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736052+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a45e8049651544c2bbe87932222589d5", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117353+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736010+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dea8b2ffd192453285486048f9d042d3", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117351+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735967+00:00", "framework": "vllm_fix_tokenizer", "intentId": "852e7704a6b6450bb63d6ee1f91dbbe9", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117348+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735925+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3986a290319048dd9ab31d2fb9b15d09", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117345+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735883+00:00", "framework": "vllm_fix_tokenizer", "intentId": "699409f98c734bac8b6ffdb9e83ec7b4", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117342+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735840+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cba64e2474b34c088e54d6cad357a44e", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117340+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735797+00:00", "framework": "vllm_fix_tokenizer", "intentId": "18bc41075cd949aa880a3c47b9e32e36", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117337+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea3c9d8ea0234a4db9b6ff5fc5187cee", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117334+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735713+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dbe913de0054427684a3490c0e7a75ec", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117331+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735670+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cbb76375731b4c94b752b0844381ea29", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117329+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735622+00:00", "framework": "vllm_fix_tokenizer", "intentId": "09c04fec92874045add8d92039c35121", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117323+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "932ee6e5868f45f386d6936b3cf74ddf", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117320+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735494+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9cd897e76fa049af80664ba04f63b6c3", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117317+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735451+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96474af7e05547d0a15efc730d104bc6", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117315+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735408+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c8ac6210032421f9156927e11487c44", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117312+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735365+00:00", "framework": "vllm_fix_tokenizer", "intentId": "007f231871cf4b269c3e0850d0354735", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117309+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735322+00:00", "framework": "vllm_fix_tokenizer", "intentId": "04342fdc2209408188f755cc04116626", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117306+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735279+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dc43e678c8f6458ead1358ae2ad06e83", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 6a47b060be..7744edb879 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2036 + "unified_success_first": 2038 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -12,7 +12,7 @@ "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 80, "text-generation|Cambricon_mlu-370-x4|vllm": 53, - "text-generation|Cambricon_mlu-370-x4|vllm-customized": 4, + "text-generation|Cambricon_mlu-370-x4|vllm-customized": 5, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82, "text-generation|Cambricon_mlu-370-x8|vllm": 55, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 42, @@ -32,14 +32,14 @@ "text-generation|Mthreads_s4000|llamacpp": 17, "text-generation|Mthreads_s4000|vllm": 103, "text-generation|Sunrise_pt-200-x1|vllm": 79, - "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 88, + "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 89, "text-generation|Vastai_va16|vllm_fix_tokenizer": 74, "text-generation|hygon_k100-ai|llamacpp": 18, "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 118 }, - "acceptedSinceRefresh": 2036, - "acceptedTotal": 2036, - "generatedAt": "2026-09-21T02:01:41.363909+00:00", + "acceptedSinceRefresh": 2038, + "acceptedTotal": 2038, + "generatedAt": "2026-09-21T02:05:57.643723+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 92887ce80f..8414d40d2a 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1168,3 +1168,5 @@ {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "submitTime": "2026-09-21T01:54:23.239188+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991516", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "modelId": "aisingapore/SEA-LION-v1-7B", "submitTime": "2026-09-21T01:57:56.851808+00:00", "targetGpu": "Biren_166m", "taskId": "4991645", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} +{"framework": "vllm-customized", "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": "2026-09-21T02:02:02.598580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x4"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"} diff --git a/manifest.json b/manifest.json index a3788b0abf..2a36a5c41f 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "9dec3dc5eb7c555336e26b5797fe65bf7f001645bdf12dc2ecceb0f5407d088b", ".modelhub_state/recent_outcomes.jsonl": "0108287b55c98ab2dc2249a82ab7ebc1206b8b7ea6855be92f670cb23fc71434", ".modelhub_state/recovery_active_tasks.jsonl": "6a226460fb0da6b3da3b69802f584e85206a221c81a7ed5c6ec4202c7495c09d", - ".modelhub_state/recovery_intents.jsonl": "a18bdb0b862f4bb2eda343a5fbc59f091dd6580268fba7c6f4f3c8acc5ab410e", - ".modelhub_state/routing_intelligence.json": "d0182110495335c1920772805729de8f615c4a628542f6865daede24c5020d4c", + ".modelhub_state/recovery_intents.jsonl": "d8f9e19b7feb85086309b6177e32648135225d8a8dfec44273a7aa5a27c7eaba", + ".modelhub_state/routing_intelligence.json": "3ffd7a886c49103d23197c3ba90d6377d27b2058d5fb66f137098fa1bf03d16f", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "7d2a4a7a43cdee205d2f8df482c8af286021f6b97c5a67d7d7e00c8e82baab37", - "outcomes/submissions.jsonl": "4e53c7ff9325fdbba7f57ee12013eecbc7b11a87ac46782a0be2716d541bb565" + "ledger/submissions.jsonl": "b46a72de941306b2c75a398c8b114f1b473a9b54e2e3df839bb2284dbfda3fbf", + "outcomes/submissions.jsonl": "733d28bdbfc819344ea4404e4d3c997563e3b0925bef5a1352498f0ae3538d29" }, - "generation": 11072, - "phase": "intent", + "generation": 11073, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T02:01:42.446609+00:00", + "updatedAt": "2026-09-21T02:05:57.924181+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 98a23c7a43..4c13aac24f 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1118,3 +1118,5 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "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", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T00:42:10.765015+00:00", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 4020783717}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:54:23.239188+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991516", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "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": 9090504988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "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": "2026-09-21T01:57:56.851808+00:00", "targetGpu": "Biren_166m", "taskId": "4991645", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "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": "2026-09-21T02:02:02.598580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "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": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}