From e63cb16db7355204752ba79dca79147549d5ced3 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 01:21:31 +0000 Subject: [PATCH] state: generation 11055 (result) --- .modelhub_state/recovery_intents.jsonl | 94 ++++++++--------------- .modelhub_state/routing_intelligence.json | 12 +-- ledger/submissions.jsonl | 3 +- manifest.json | 14 ++-- outcomes/submissions.jsonl | 2 + 5 files changed, 49 insertions(+), 76 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index cabb023079..4f9a5ccae7 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1886,38 +1886,38 @@ {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117262+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734657+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5572f6ca884e47739141284fe6081b21", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117281+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.734936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b6bbef3120454144a22fc97f515a87d2", "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": "Biren_166m", "taskId": "4990910", "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117326+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.735580+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cf7ec8f561de46e2a322926d72f61291", "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": "Biren_166m", "taskId": "4990935", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937091+00:00", "framework": "vllm", "intentId": "77d986480bb546dd8d45840763641351", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937219+00:00", "framework": "vllm", "intentId": "c21d52e04caa44c3bd1df267d94256e1", "lastModified": "2026-08-24T19:44:39+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a8", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937273+00:00", "framework": "vllm", "intentId": "0abbe3fe66e042c4bbf18c2e7bb189cf", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937324+00:00", "framework": "vllm", "intentId": "22c8fb5857c4426b80fe9a5384e4c9a9", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937374+00:00", "framework": "vllm", "intentId": "468bcab5bbc04b9f891482f9bbaffd75", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937422+00:00", "framework": "vllm", "intentId": "8a5ccb530f0f4abab765b82e98b38104", "lastModified": "2026-08-24T19:39:57+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937471+00:00", "framework": "vllm", "intentId": "821b6c8df4904e1c9ed7cf3ae12dd327", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937520+00:00", "framework": "vllm", "intentId": "fbef0bb5776a470499ab0e0a13fa71f0", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937569+00:00", "framework": "vllm", "intentId": "1fc27a3677cb4d51a5883fefbcb11f1e", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937617+00:00", "framework": "vllm_tokenizer_patch", "intentId": "55308352ae1445ad83397538cdab54b5", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937661+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4b73d69b7c4c4d5c9531b9ce61e05409", "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": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937711+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a2dfd00a0944f699441aacd85790bf2", "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}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937753+00:00", "framework": "vllm-customized", "intentId": "0f87e42be4c648a093888cb9b46cdced", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937817+00:00", "framework": "vllm-customized", "intentId": "3832f8d14ef54308b7061cb1c4e2c1f6", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937878+00:00", "framework": "vllm-customized", "intentId": "ecc9642000994a18a7d67c089b8545ad", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937938+00:00", "framework": "vllm-customized", "intentId": "eb2b4a7e731443b0bd772880a4c7bf2a", "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": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937997+00:00", "framework": "vllm-customized", "intentId": "a749022e262948a6ba6aa47eea47cc39", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938056+00:00", "framework": "vllm-customized", "intentId": "a4dc9dae0fc34124832b07bb5ac405b6", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938116+00:00", "framework": "vllm-customized", "intentId": "e59554ed94a8439297271e52ca7930b0", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938175+00:00", "framework": "vllm", "intentId": "54c1c686a57943e0b5419e4027fadaaa", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938221+00:00", "framework": "vllm", "intentId": "7f41cc04b33a4bdb8afadd1cd7bb28da", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938264+00:00", "framework": "vllm", "intentId": "5dc256a77c30466aa6dbfeead09c302d", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938307+00:00", "framework": "vllm", "intentId": "b32f6e2560d342888ddb406feed63d24", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938350+00:00", "framework": "vllm", "intentId": "6a6d66d8ab494ed3883fdd335528bf12", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938392+00:00", "framework": "vllm", "intentId": "bb6195459dd3407cb90aecdf4c40302f", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938435+00:00", "framework": "vllm", "intentId": "a131a0ed6ab842068c1dac70ae59a24e", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938495+00:00", "framework": "vllm_fix_tokenizer", "intentId": "068dd0a17c844f07b37e859635a41861", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938552+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15bde2dc5b5a4b388a323147e0a4d9c8", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation"} -{"batchId": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938622+00:00", "framework": "vllm_fix_tokenizer", "intentId": "941eb72ce4ce455ab464aaa7bea8ddc8", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938697+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d1e38f128c2b4aed83dcfd8d9c59d128", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938753+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c0241439eb454c13a187d21167c5a622", "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": "894eae6b118542beb2b1c7a74004e89b", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79f1949e9b554e83a620c1d6a5411da3", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111047+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937938+00:00", "framework": "vllm-customized", "intentId": "eb2b4a7e731443b0bd772880a4c7bf2a", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991028", "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111078+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938552+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15bde2dc5b5a4b388a323147e0a4d9c8", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111089+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938810+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79f1949e9b554e83a620c1d6a5411da3", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111087+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938753+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c0241439eb454c13a187d21167c5a622", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111084+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938697+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d1e38f128c2b4aed83dcfd8d9c59d128", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111081+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938622+00:00", "framework": "vllm_fix_tokenizer", "intentId": "941eb72ce4ce455ab464aaa7bea8ddc8", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111076+00:00", "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938495+00:00", "framework": "vllm_fix_tokenizer", "intentId": "068dd0a17c844f07b37e859635a41861", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111073+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938435+00:00", "framework": "vllm", "intentId": "a131a0ed6ab842068c1dac70ae59a24e", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111070+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938392+00:00", "framework": "vllm", "intentId": "bb6195459dd3407cb90aecdf4c40302f", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111068+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938350+00:00", "framework": "vllm", "intentId": "6a6d66d8ab494ed3883fdd335528bf12", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111065+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938307+00:00", "framework": "vllm", "intentId": "b32f6e2560d342888ddb406feed63d24", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111062+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938264+00:00", "framework": "vllm", "intentId": "5dc256a77c30466aa6dbfeead09c302d", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111060+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938221+00:00", "framework": "vllm", "intentId": "7f41cc04b33a4bdb8afadd1cd7bb28da", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111057+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938175+00:00", "framework": "vllm", "intentId": "54c1c686a57943e0b5419e4027fadaaa", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111054+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938116+00:00", "framework": "vllm-customized", "intentId": "e59554ed94a8439297271e52ca7930b0", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111052+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.938056+00:00", "framework": "vllm-customized", "intentId": "a4dc9dae0fc34124832b07bb5ac405b6", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111049+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937997+00:00", "framework": "vllm-customized", "intentId": "a749022e262948a6ba6aa47eea47cc39", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111044+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937878+00:00", "framework": "vllm-customized", "intentId": "ecc9642000994a18a7d67c089b8545ad", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111041+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937817+00:00", "framework": "vllm-customized", "intentId": "3832f8d14ef54308b7061cb1c4e2c1f6", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111038+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937753+00:00", "framework": "vllm-customized", "intentId": "0f87e42be4c648a093888cb9b46cdced", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111035+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937711+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8a2dfd00a0944f699441aacd85790bf2", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111033+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937661+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4b73d69b7c4c4d5c9531b9ce61e05409", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111030+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937617+00:00", "framework": "vllm_tokenizer_patch", "intentId": "55308352ae1445ad83397538cdab54b5", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111027+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937569+00:00", "framework": "vllm", "intentId": "1fc27a3677cb4d51a5883fefbcb11f1e", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111024+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937520+00:00", "framework": "vllm", "intentId": "fbef0bb5776a470499ab0e0a13fa71f0", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111021+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937471+00:00", "framework": "vllm", "intentId": "821b6c8df4904e1c9ed7cf3ae12dd327", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111018+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937422+00:00", "framework": "vllm", "intentId": "8a5ccb530f0f4abab765b82e98b38104", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111015+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937374+00:00", "framework": "vllm", "intentId": "468bcab5bbc04b9f891482f9bbaffd75", "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": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111012+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937324+00:00", "framework": "vllm", "intentId": "22c8fb5857c4426b80fe9a5384e4c9a9", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111009+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937273+00:00", "framework": "vllm", "intentId": "0abbe3fe66e042c4bbf18c2e7bb189cf", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.111005+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937219+00:00", "framework": "vllm", "intentId": "c21d52e04caa44c3bd1df267d94256e1", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "894eae6b118542beb2b1c7a74004e89b", "completedAt": "2026-09-21T01:21:31.110990+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:17:18.937091+00:00", "framework": "vllm", "intentId": "77d986480bb546dd8d45840763641351", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117413+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T01:09:52.736940+00:00", "framework": "vllm", "intentId": "1916c1551b6d41419ba32c2dbfb750eb", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "089686064200439b8fd0be0bb2b376d3", "completedAt": "2026-09-21T01:17:18.117410+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"} @@ -2188,33 +2188,3 @@ {"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837107+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901997+00:00", "framework": "vllm", "intentId": "b3c3d7a81ebe43afa19ac0b530d4afaf", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837104+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901938+00:00", "framework": "vllm", "intentId": "c1e95ddfd79149d4b777d00897081d58", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837101+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901883+00:00", "framework": "vllm", "intentId": "02464100e1c84e29a46858eb2a7fd8bf", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837098+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901823+00:00", "framework": "vllm", "intentId": "4c9d8179e3a8475cbc857df0821eb4c4", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837095+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901781+00:00", "framework": "vllm_fix_tokenizer", "intentId": "723c76e37bdc4a0798da4677f4af9997", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837092+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901738+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1127bf3d21bb488baa10c5aa7d72b084", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837089+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901696+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4d18e9b9b44b442dafb7e61c5a9ec362", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837087+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901637+00:00", "framework": "vllm_fix_tokenizer", "intentId": "846815b229c54690a43a378e6e5dd54f", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837084+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901595+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bddbc069989c409490b51a00c96a7df9", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837081+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901553+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6f8bd7f74ab44e09b6c472190dcc4b34", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837078+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901511+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f0730667fcb44d729999948d2d25ff04", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837075+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901469+00:00", "framework": "vllm_fix_tokenizer", "intentId": "158e0c663e214b9cb3e2a5c61c3e7bd5", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837072+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901427+00:00", "framework": "vllm_fix_tokenizer", "intentId": "24df829a31374f96867aef56c0c1743d", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837070+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901385+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5d9ecacf734487abe95ba3b6b8c25c5", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837067+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901343+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31de58c45c254e0f8591dcb6b1d52d30", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837064+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901300+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e18d6d954927494d8d5ef048e8f9afe6", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837062+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901251+00:00", "framework": "vllm_fix_tokenizer", "intentId": "37a8678929ac4935aea484b7fd5eee47", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837059+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901209+00:00", "framework": "vllm_fix_tokenizer", "intentId": "14b3f463a4df496ab1da52366e27a29b", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837057+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901167+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d38bd5748d74aee8ff00d372a6b5b05", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837054+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901125+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6ae816bdc9fb4cf6afc33742cdcf2b7e", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837051+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901083+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7d713b564bdb495d9c63da1a628300d9", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837048+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.901040+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b6dec9151cd043f6ad896de3b6efc426", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837045+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900998+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c060e2ac89da49b5b50f54f7b70c8f2b", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837042+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900954+00:00", "framework": "vllm_fix_tokenizer", "intentId": "169b8ccc8e284f37b1de30ccd55773c1", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837040+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900912+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5b844ca385f3468a95d8a33b17151a2f", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837036+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900870+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ccba5d3e8b4b406ebe9512203e611ebd", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837033+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900827+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d790c3bef724dbaa15ffdfdd3357801", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837031+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900785+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d6876d93a124e51878d69081495a7f4", "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": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837028+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900736+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c84e696fa99490388bc09163ed3c8ed", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837024+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900694+00:00", "framework": "vllm_fix_tokenizer", "intentId": "468c10be4a874a819088a82dc78a2eaf", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837021+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900646+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a1b4187df0c74cbe9b8d9a7544880d64", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837018+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900603+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aad74f15aefa49fcb4d7a7ac710b8763", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "a9f03997771542de9d155ab568096558", "completedAt": "2026-09-21T00:20:16.837016+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T00:12:49.900561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3dec5f6f751c4883a515106d9195e5d3", "repoId": "RedHatAI/starcoder2-3b-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 b07117e73a..aa0da5ab4d 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2026 + "unified_success_first": 2028 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-customized": 4, "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": 40, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 41, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 94, "text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -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": 87, + "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 88, "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": 2026, - "acceptedTotal": 2026, - "generatedAt": "2026-09-21T01:17:18.051736+00:00", + "acceptedSinceRefresh": 2028, + "acceptedTotal": 2028, + "generatedAt": "2026-09-21T01:21:31.049521+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index ff6a551782..c89c6ad086 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1006,7 +1006,6 @@ {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T03:57:37.934664+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970335", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T03:58:35.458351+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970351", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T03:58:41.304973+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} @@ -1161,3 +1160,5 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"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": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "submitTime": "2026-09-21T01:11:59.475916+00:00", "targetGpu": "Biren_166m", "taskId": "4990935", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-21T01:17:52.505387+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"} diff --git a/manifest.json b/manifest.json index dc708fa38d..4de0ee74d6 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "87ea93bf42a8a1e24e156ef53e31bb1f4495dd95733206eb0979243c703bdc7f", ".modelhub_state/recent_outcomes.jsonl": "bfffd6af93a9d04b368110149eca10ab996989d09685a15b5c02f02824787e9b", ".modelhub_state/recovery_active_tasks.jsonl": "47a448855a5cf5902e5effcee152eb9a864fea15488a4004b1350ef23b18b082", - ".modelhub_state/recovery_intents.jsonl": "68fec30964a2470cf35af16e4d9bedb9e25065cf8267f61fee5278b4bf6d55aa", - ".modelhub_state/routing_intelligence.json": "7eb4badffe639ab62245ebeca66ebfd381b6f4ab910458ac0ef6f058152cab30", + ".modelhub_state/recovery_intents.jsonl": "11d3af2b3193fc3f540efe14aa25e9bb2dde961a0b44d735d71f4b1836601a4e", + ".modelhub_state/routing_intelligence.json": "be22eb901d2c44172369aa9ff619b81df1a74d46300618e4a078301b73d53e2e", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "3787bf8090cef9d15c9f9c0f69a6870580ca22eb1b1cd3625d3b1c9bc66a449d", - "outcomes/submissions.jsonl": "3b3e2edba320e23090862f04bfc0729f19db94075763b82398691c80097cb4e8" + "ledger/submissions.jsonl": "92c6aaeda51b218745c0ea0aa916d78714bf59452516b1643a9e90e8233b4d47", + "outcomes/submissions.jsonl": "08501a2feebef9b57e30282cc8a33838f38a59599b4e05792198d310cc8b7ec4" }, - "generation": 11054, - "phase": "intent", + "generation": 11055, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T01:17:19.137396+00:00", + "updatedAt": "2026-09-21T01:21:31.261124+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 4c0719a0f1..ca68a85097 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1120,3 +1120,5 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "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": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "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": 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": "2026-09-21T01:11:59.475916+00:00", "targetGpu": "Biren_166m", "taskId": "4990935", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-21T01:17:52.505387+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991028", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "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": 507443106}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "verifyResult": null}