From c6c47c414b73cc6aac0ee25b67457a03f9d935d3 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 08:16:22 +0000 Subject: [PATCH] state: generation 11324 (result) --- .modelhub_state/recovery_intents.jsonl | 107 ++++++++-------------- .modelhub_state/routing_intelligence.json | 10 +- ledger/submissions.jsonl | 1 + manifest.json | 14 +-- outcomes/submissions.jsonl | 1 + 5 files changed, 50 insertions(+), 83 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 93f62269c..d242feca7 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1999,42 +1999,42 @@ {"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315220+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.765282+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4c5e1738deba44a1b92914f0b5a8a929", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "reason": null, "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4996756", "taskType": "text-generation"} {"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315299+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.766876+00:00", "framework": "vllm", "intentId": "a5af8f7f39a54296a2ed3edaf0124420", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4996781", "taskType": "text-generation"} {"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315333+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767712+00:00", "framework": "vllm-customized", "intentId": "de67b41a706d4c9b8c0e56258c4643bc", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "reason": null, "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125132+00:00", "framework": "vllm-customized", "intentId": "a26ea7938dc94d4091a4cbe156cc1ab0", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125277+00:00", "framework": "vllm-customized", "intentId": "2676465be98249de9e19d1984aa38ebc", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125349+00:00", "framework": "vllm-customized", "intentId": "00ceebf321ff4788bac1eb507aa38445", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125409+00:00", "framework": "vllm-customized", "intentId": "ac863f030f584455907bf3d1744a74f1", "lastModified": "2026-08-24T20:30:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125468+00:00", "framework": "vllm-customized", "intentId": "10d2af58fce14a56b9343f75381d0b9f", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125526+00:00", "framework": "vllm-customized", "intentId": "610bfc3cde544bd688248ef7ec7c32a8", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125584+00:00", "framework": "vllm-customized", "intentId": "a8ed45a1df7c48e1b397f5702e9385d2", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125642+00:00", "framework": "vllm-customized", "intentId": "a805cd2d97ec422da4481e978d11ac33", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125737+00:00", "framework": "vllm-customized", "intentId": "661457e8fda14a4e87f94b2ae7fbd37c", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125796+00:00", "framework": "vllm-customized", "intentId": "eefa8f825dba45839d0c0fd8c8317b75", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125854+00:00", "framework": "vllm-customized", "intentId": "c2397a88a700409884255cd4ceac9e78", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125912+00:00", "framework": "vllm-customized", "intentId": "7ac62c3d6d254551b1196a595ee8d817", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125969+00:00", "framework": "vllm-customized", "intentId": "f0773bdaf3714cb3beadadbdc2ba7a05", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126027+00:00", "framework": "vllm-customized", "intentId": "8267f723d7f24c9bb934cb82b77e04e0", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126084+00:00", "framework": "vllm-customized", "intentId": "49f939dda5c64ba881971afbaca2e265", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126142+00:00", "framework": "vllm-customized", "intentId": "b1c878ed4532494995e0e3a1c12408f2", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126200+00:00", "framework": "vllm-customized", "intentId": "5331e795426a45ae912a46a138ffab8c", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126258+00:00", "framework": "vllm-customized", "intentId": "a9408af601934ff19c0934155b331caa", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126325+00:00", "framework": "vllm-customized", "intentId": "c543636f514d461ca96beda2bce5e0cd", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126388+00:00", "framework": "vllm-customized", "intentId": "953db7690844414ebc53e2bb995b392b", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126446+00:00", "framework": "vllm-customized", "intentId": "ec2a9bb610ab4ac7b59e5c762b2c13c9", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126505+00:00", "framework": "vllm", "intentId": "1439f29f08524d2ba67072c192b474d7", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126563+00:00", "framework": "vllm", "intentId": "dd85fce80e5545eaaf294e74d29381ee", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126620+00:00", "framework": "vllm", "intentId": "55e5105a51c8499b86389567f4db558a", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126684+00:00", "framework": "vllm", "intentId": "0cd796e77e424fbca904186c720141cb", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126736+00:00", "framework": "vllm", "intentId": "3f374cb15c944e88aa8f0b3f4e20620e", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126803+00:00", "framework": "vllm", "intentId": "b3feabdf9bb94163b2f7b4a49eb1a0b3", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126853+00:00", "framework": "vllm", "intentId": "6206050e79f24ed389d89018c92af3f8", "lastModified": "2026-09-09T13:42:58+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126903+00:00", "framework": "vllm", "intentId": "0dc8605254ac478496cee133f7b44cb8", "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": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126952+00:00", "framework": "vllm", "intentId": "31f45bd2446042318bf83c44f8ffdbc2", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127002+00:00", "framework": "vllm", "intentId": "1dd7d3d2d17947428d51853e127b5a37", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127060+00:00", "framework": "vllm", "intentId": "dea98d25c0704d2490b41d65e43aecdc", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127117+00:00", "framework": "vllm", "intentId": "d8e33d1823b949bcaf896a8daec722ec", "lastModified": "2026-08-24T19:54:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127174+00:00", "framework": "vllm", "intentId": "d8aff6a5552345c6aabfa8a2186a5135", "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": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127231+00:00", "framework": "vllm", "intentId": "a7743eff51694235ba4577c5edb0a5c8", "lastModified": "2026-08-24T20:02:14+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127288+00:00", "framework": "vllm", "intentId": "65cef4d446084037bb13153d52b7c872", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466021+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126142+00:00", "framework": "vllm-customized", "intentId": "b1c878ed4532494995e0e3a1c12408f2", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "reason": null, "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466082+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127288+00:00", "framework": "vllm", "intentId": "65cef4d446084037bb13153d52b7c872", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466079+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127231+00:00", "framework": "vllm", "intentId": "a7743eff51694235ba4577c5edb0a5c8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466076+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127174+00:00", "framework": "vllm", "intentId": "d8aff6a5552345c6aabfa8a2186a5135", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466072+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127117+00:00", "framework": "vllm", "intentId": "d8e33d1823b949bcaf896a8daec722ec", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466070+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127060+00:00", "framework": "vllm", "intentId": "dea98d25c0704d2490b41d65e43aecdc", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466067+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.127002+00:00", "framework": "vllm", "intentId": "1dd7d3d2d17947428d51853e127b5a37", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466064+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126952+00:00", "framework": "vllm", "intentId": "31f45bd2446042318bf83c44f8ffdbc2", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466061+00:00", "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126903+00:00", "framework": "vllm", "intentId": "0dc8605254ac478496cee133f7b44cb8", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466058+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126853+00:00", "framework": "vllm", "intentId": "6206050e79f24ed389d89018c92af3f8", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466055+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126803+00:00", "framework": "vllm", "intentId": "b3feabdf9bb94163b2f7b4a49eb1a0b3", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466053+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126736+00:00", "framework": "vllm", "intentId": "3f374cb15c944e88aa8f0b3f4e20620e", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466049+00:00", "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126684+00:00", "framework": "vllm", "intentId": "0cd796e77e424fbca904186c720141cb", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466046+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126620+00:00", "framework": "vllm", "intentId": "55e5105a51c8499b86389567f4db558a", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466043+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126563+00:00", "framework": "vllm", "intentId": "dd85fce80e5545eaaf294e74d29381ee", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466040+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126505+00:00", "framework": "vllm", "intentId": "1439f29f08524d2ba67072c192b474d7", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466037+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126446+00:00", "framework": "vllm-customized", "intentId": "ec2a9bb610ab4ac7b59e5c762b2c13c9", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466034+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126388+00:00", "framework": "vllm-customized", "intentId": "953db7690844414ebc53e2bb995b392b", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466030+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126325+00:00", "framework": "vllm-customized", "intentId": "c543636f514d461ca96beda2bce5e0cd", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466027+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126258+00:00", "framework": "vllm-customized", "intentId": "a9408af601934ff19c0934155b331caa", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466024+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126200+00:00", "framework": "vllm-customized", "intentId": "5331e795426a45ae912a46a138ffab8c", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466018+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126084+00:00", "framework": "vllm-customized", "intentId": "49f939dda5c64ba881971afbaca2e265", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466015+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.126027+00:00", "framework": "vllm-customized", "intentId": "8267f723d7f24c9bb934cb82b77e04e0", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466011+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125969+00:00", "framework": "vllm-customized", "intentId": "f0773bdaf3714cb3beadadbdc2ba7a05", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466008+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125912+00:00", "framework": "vllm-customized", "intentId": "7ac62c3d6d254551b1196a595ee8d817", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466004+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125854+00:00", "framework": "vllm-customized", "intentId": "c2397a88a700409884255cd4ceac9e78", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.466001+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125796+00:00", "framework": "vllm-customized", "intentId": "eefa8f825dba45839d0c0fd8c8317b75", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465997+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125737+00:00", "framework": "vllm-customized", "intentId": "661457e8fda14a4e87f94b2ae7fbd37c", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465995+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125642+00:00", "framework": "vllm-customized", "intentId": "a805cd2d97ec422da4481e978d11ac33", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465991+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125584+00:00", "framework": "vllm-customized", "intentId": "a8ed45a1df7c48e1b397f5702e9385d2", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465988+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125526+00:00", "framework": "vllm-customized", "intentId": "610bfc3cde544bd688248ef7ec7c32a8", "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": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465985+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125468+00:00", "framework": "vllm-customized", "intentId": "10d2af58fce14a56b9343f75381d0b9f", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465973+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125409+00:00", "framework": "vllm-customized", "intentId": "ac863f030f584455907bf3d1744a74f1", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465969+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125349+00:00", "framework": "vllm-customized", "intentId": "00ceebf321ff4788bac1eb507aa38445", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465965+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125277+00:00", "framework": "vllm-customized", "intentId": "2676465be98249de9e19d1984aa38ebc", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "7dd2dfc02db643c1b324bbebd0018229", "completedAt": "2026-09-21T08:16:22.465948+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:11:15.125132+00:00", "framework": "vllm-customized", "intentId": "a26ea7938dc94d4091a4cbe156cc1ab0", "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": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315329+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767639+00:00", "framework": "vllm-customized", "intentId": "e23c9fd8517b4dac849715ba32859ee2", "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": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315327+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767575+00:00", "framework": "vllm-customized", "intentId": "7af34205855749fda78ab521eb660c4a", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "8c273c92141d43488fec73023ec49660", "completedAt": "2026-09-21T08:11:14.315324+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:02:53.767482+00:00", "framework": "vllm-customized", "intentId": "99921f6d1e394490a08418b051c47861", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} @@ -2300,38 +2300,3 @@ {"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115399+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479234+00:00", "framework": "vllm-customized", "intentId": "d7a41a1589bb4febbf62ddc47f3359f1", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115395+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479176+00:00", "framework": "vllm-customized", "intentId": "fce3333016464023b3c142c2d8c39271", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} {"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115393+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479118+00:00", "framework": "vllm-customized", "intentId": "422d6121868946509a5debc4e6078f90", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115390+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479060+00:00", "framework": "vllm-customized", "intentId": "803793a9e44b4cddba6fd376302c42c7", "repoId": "RedHatAI/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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115387+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.479002+00:00", "framework": "vllm-customized", "intentId": "caba5d698c8846b5b71b68398b8b8cd6", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115383+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478944+00:00", "framework": "vllm-customized", "intentId": "a9a3e024c6e54bb8accfc544120ebfe5", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115380+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478887+00:00", "framework": "vllm-customized", "intentId": "f35d96f2dfeb4f2a91dbef2792e11487", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115377+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478828+00:00", "framework": "vllm-customized", "intentId": "1b9f9bc717764a16addd434575734c7f", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115373+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478771+00:00", "framework": "vllm-customized", "intentId": "5d22f49302104b3aa340a94f6d9853ed", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115370+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478712+00:00", "framework": "vllm-customized", "intentId": "7842e2f8bd44450ea9fbbef85d1a297f", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115366+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478639+00:00", "framework": "vllm-customized", "intentId": "f0fbe9d03476421a8701510cff06f7b0", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115364+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478581+00:00", "framework": "vllm-customized", "intentId": "cb9901f979254abf9dbff48f7de6a776", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115361+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478522+00:00", "framework": "vllm-customized", "intentId": "19227d0669d044e1bbc7b4682102a702", "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": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115358+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478465+00:00", "framework": "vllm-customized", "intentId": "f185345bdcb94c3880e47e915aa308d8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115355+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478407+00:00", "framework": "vllm-customized", "intentId": "5d376ab0882e47b6a95bc51bfbe7b9f0", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115351+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478348+00:00", "framework": "vllm-customized", "intentId": "af029da34bd64bbdb0bb1656c92e24af", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115345+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478206+00:00", "framework": "vllm-customized", "intentId": "f3d8fd2cca4746b3b519ee111f079c5d", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115341+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478146+00:00", "framework": "vllm-customized", "intentId": "23bbab818df1430a8e9b4de71848e0f3", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115337+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.478083+00:00", "framework": "vllm-customized", "intentId": "eb2177410c654996bab3f3736620c477", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "1786d9feeb62414d967e9337f7ba4da1", "completedAt": "2026-09-21T06:38:48.115311+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:33:08.477945+00:00", "framework": "vllm-customized", "intentId": "83f0d0c592d24fdb98affeb064f1e55e", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669607+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398071+00:00", "framework": "vllm-customized", "intentId": "2a066644f1e548fd9121f1b78ca87dda", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669604+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.398013+00:00", "framework": "vllm-customized", "intentId": "878d497579ab44d5baa6b918ba0aaff0", "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": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669602+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397956+00:00", "framework": "vllm-customized", "intentId": "30a94939f5964518b2330fe23803e0e1", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669599+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397895+00:00", "framework": "vllm-customized", "intentId": "ac2fff845ede4e6db0a7e90796dce0b2", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669596+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397815+00:00", "framework": "vllm-customized", "intentId": "6699c79379af416495fadb2a2bb5f547", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669594+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397757+00:00", "framework": "vllm-customized", "intentId": "9439ad472a144bde8a751b64d4b8959e", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669591+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397700+00:00", "framework": "vllm-customized", "intentId": "9f65bb901dba40a990860f323cade531", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669588+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397631+00:00", "framework": "vllm-customized", "intentId": "511e4a8e2c4b4d2894cebe63b080ce28", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669585+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397574+00:00", "framework": "vllm-customized", "intentId": "eb4fde14582f4513bef9b3721f7cddfc", "repoId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669582+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397518+00:00", "framework": "vllm-customized", "intentId": "9dec1cbd9d0a4eaf8bc2e303b5f29b6d", "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": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669579+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397461+00:00", "framework": "vllm-customized", "intentId": "4d3798bcc3ef44d9bf02d1f9c8520199", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669576+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397404+00:00", "framework": "vllm-customized", "intentId": "168afc3af4e24c67949dbb90e5cd8aa6", "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": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669573+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397347+00:00", "framework": "vllm-customized", "intentId": "29b6a3fa586041c48fc73d55cbbf5266", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669570+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397290+00:00", "framework": "vllm-customized", "intentId": "ec2fb55fdae94667855de87071d2a35b", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669567+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397233+00:00", "framework": "vllm-customized", "intentId": "f7ac0ba7d47447209fe10abc780cf0c8", "repoId": "neuralmagic/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": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669565+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397176+00:00", "framework": "vllm-customized", "intentId": "9d71bca1a7d449c0aacd93db4a8a4799", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669562+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397111+00:00", "framework": "vllm-customized", "intentId": "13a6d043f4334d8ab928bb0eb5e2c117", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} -{"batchId": "56bea225aab940a1bb2497ea0c449398", "completedAt": "2026-09-21T06:33:07.669559+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T06:25:22.397054+00:00", "framework": "vllm-customized", "intentId": "ea5f73eb3c6e4078b7a2e66235a51c43", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 7cea407da..8291eac99 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2138 + "unified_success_first": 2139 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "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": 48, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 49, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 96, "text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 120 }, - "acceptedSinceRefresh": 2138, - "acceptedTotal": 2138, - "generatedAt": "2026-09-21T08:11:14.252402+00:00", + "acceptedSinceRefresh": 2139, + "acceptedTotal": 2139, + "generatedAt": "2026-09-21T08:16:22.396297+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 1766dc487..37a4193c7 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1169,3 +1169,4 @@ {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "submitTime": "2026-09-21T08:03:50.463371+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4996756", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "submitTime": "2026-09-21T08:07:48.338371+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4996781", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "modelId": "XHToken/Spark-X2.5-4B", "submitTime": "2026-09-21T08:09:36.692226+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-21T08:11:51.336512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index e3068a92c..f95d6eca5 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "56206916bd251aff8514079cb7cc354f9b75586442b701fa6494a14e681e7d86", ".modelhub_state/recent_outcomes.jsonl": "4ae896458f2dd9e406cc1ad6c7fd36db5bbd615ceaed0827c9fd9e7a0f9e44a1", ".modelhub_state/recovery_active_tasks.jsonl": "1e09ad222938a438468c9d7471b3d30095a05ad63677fe58dc6e1e6255d5aa81", - ".modelhub_state/recovery_intents.jsonl": "8e9aa67c1ca30db88c480baa0bd0ff62160cd66065bee782a21b3049121dba49", - ".modelhub_state/routing_intelligence.json": "6e326f0ff65d04c7bde96a85c72ddecb5e65bbab5e3152e1d144ca66a94be144", + ".modelhub_state/recovery_intents.jsonl": "2777dd397745df01ddf8d1f33480e70cc1f0bc0468f93f505367ab6a51ac88c9", + ".modelhub_state/routing_intelligence.json": "46e6f11f2821bc8571088c5b3514226002e705bec814da6d2223f2a1f4d7ed22", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "0fe7aab1f17c95c45686164eb2495bea6493cde3f38a247af537db4c27dd4b49", - "outcomes/submissions.jsonl": "1c392b18fb581fffa74c64cc50046f5164462f93659d9cf140affc40c319e223" + "ledger/submissions.jsonl": "be4ea2d9ae1716419ccff2017cd2fde1637fefeaf551f46ab9dd84860c222867", + "outcomes/submissions.jsonl": "832378c55c1784d3e01abe08522c0b979b68ee93e4dc349784511b3f799c3caf" }, - "generation": 11323, - "phase": "intent", + "generation": 11324, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T08:11:15.334151+00:00", + "updatedAt": "2026-09-21T08:16:22.627984+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 4db70637a..8d495a50b 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1129,3 +1129,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "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": 12020499021, "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": 12020499021}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:03:50.463371+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4996756", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:07:48.338371+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4996781", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:09:36.692226+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T08:11:51.336512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "taskType": "text-generation", "verifyResult": null}