From 3629648c37449b8180773115a3432bf4826f0495 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 17:22:42 +0000 Subject: [PATCH] state: generation 11575 (result) --- .modelhub_state/recovery_intents.jsonl | 74 ++++++++--------------- .modelhub_state/routing_intelligence.json | 10 +-- ledger/submissions.jsonl | 2 +- manifest.json | 14 ++--- outcomes/submissions.jsonl | 1 + 5 files changed, 39 insertions(+), 62 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index f46e24117e..d969dfcb73 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2161,31 +2161,31 @@ {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427620+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.705956+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7e7038801d2841db9196fdf92eecc9db", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "5004581", "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427653+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706511+00:00", "framework": "vllm", "intentId": "a946c4d8d67145c2a4bf8e3112cb4e8e", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "reason": null, "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427655+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706557+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1408ca1d3cfa42449273b93f7c7042c8", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497295+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f2af51898f2d422fabed410da78a0b34", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497403+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e44169b51f914ee6900fa2a1fdc19b1e", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497449+00:00", "framework": "vllm-customized", "intentId": "ea47fbbb9a8f47dbbca6626d4ada41ae", "lastModified": "2026-08-24T20:07:32+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497517+00:00", "framework": "vllm-customized", "intentId": "697ff365f2ad40ed831c8ca4be8e4675", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497612+00:00", "framework": "vllm-customized", "intentId": "6a9a63b578894b6aaaa31b2a79a803e8", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497685+00:00", "framework": "vllm-customized", "intentId": "a2e7bdd7b48b4cc289341d664a2d4369", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497744+00:00", "framework": "vllm-customized", "intentId": "f5a6848026084d4abde94655ea3d6ee8", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497803+00:00", "framework": "vllm-customized", "intentId": "277d46a45e504fd0bb36cbf5d3a207f8", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497861+00:00", "framework": "vllm-customized", "intentId": "44492baee8e64456a47c47c62b317921", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497920+00:00", "framework": "vllm-customized", "intentId": "5b05e0b5a4a2430ba883700a9b00e819", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497978+00:00", "framework": "vllm-customized", "intentId": "1dd80c6849ce4bde83470ec89b3aec67", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498050+00:00", "framework": "vllm-customized", "intentId": "a65e2095832343449bdb61b831ba7b32", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498117+00:00", "framework": "vllm-customized", "intentId": "0ecdca2c3c0a4e598c587f4861545643", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498176+00:00", "framework": "vllm-customized", "intentId": "2d8e15dd3ce1418dbd1db8ee99865e4f", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498234+00:00", "framework": "vllm-customized", "intentId": "747eda1dbafe4342b94ed38bda23d415", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498292+00:00", "framework": "vllm-customized", "intentId": "8da283666f8549d499d40b8042b3195b", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498351+00:00", "framework": "vllm-customized", "intentId": "e51eb34d070948e29a6072f2860c3eb4", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498406+00:00", "framework": "vllm-customized", "intentId": "e6fe791d1cc44443a0d9be847a3e460d", "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": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498460+00:00", "framework": "vllm-customized", "intentId": "eb2a80481ca74061ab1aabc24875084c", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498534+00:00", "framework": "vllm-customized", "intentId": "b81de202590441989dc13a09f8ed9e6d", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498587+00:00", "framework": "vllm-customized", "intentId": "142c8f774ba9469087994045a2a63a64", "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": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498641+00:00", "framework": "vllm-customized", "intentId": "b22dfe70d4124f8aa729e250669278c9", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498700+00:00", "framework": "vllm", "intentId": "a5df71d38d964ab69f7f50d7fd0e94e1", "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": "b053643791784de79f017488ac83d21b", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498759+00:00", "framework": "vllm", "intentId": "a2609c244ae04dd3ade72ca48f1880b4", "lastModified": "2026-08-24T18:15:08+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} -{"batchId": "b053643791784de79f017488ac83d21b", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498817+00:00", "framework": "vllm", "intentId": "3cf1f8a68f1540cf8c061c7882e351ed", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281128+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498117+00:00", "framework": "vllm-customized", "intentId": "0ecdca2c3c0a4e598c587f4861545643", "lastModified": "2026-08-24T18:50:21+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281170+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498817+00:00", "framework": "vllm", "intentId": "3cf1f8a68f1540cf8c061c7882e351ed", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281166+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498759+00:00", "framework": "vllm", "intentId": "a2609c244ae04dd3ade72ca48f1880b4", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281162+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498700+00:00", "framework": "vllm", "intentId": "a5df71d38d964ab69f7f50d7fd0e94e1", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281158+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498641+00:00", "framework": "vllm-customized", "intentId": "b22dfe70d4124f8aa729e250669278c9", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281154+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498587+00:00", "framework": "vllm-customized", "intentId": "142c8f774ba9469087994045a2a63a64", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281151+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498534+00:00", "framework": "vllm-customized", "intentId": "b81de202590441989dc13a09f8ed9e6d", "repoId": "TokenRhythm/NeoHorse-1-9B", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281147+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498460+00:00", "framework": "vllm-customized", "intentId": "eb2a80481ca74061ab1aabc24875084c", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281144+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498406+00:00", "framework": "vllm-customized", "intentId": "e6fe791d1cc44443a0d9be847a3e460d", "repoId": "XHToken/Spark-X2.5-1.7B", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281140+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498351+00:00", "framework": "vllm-customized", "intentId": "e51eb34d070948e29a6072f2860c3eb4", "repoId": "TokenRhythm/NeoHorse-1-4B", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281137+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498292+00:00", "framework": "vllm-customized", "intentId": "8da283666f8549d499d40b8042b3195b", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281133+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498234+00:00", "framework": "vllm-customized", "intentId": "747eda1dbafe4342b94ed38bda23d415", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281130+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498176+00:00", "framework": "vllm-customized", "intentId": "2d8e15dd3ce1418dbd1db8ee99865e4f", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281125+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.498050+00:00", "framework": "vllm-customized", "intentId": "a65e2095832343449bdb61b831ba7b32", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281122+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497978+00:00", "framework": "vllm-customized", "intentId": "1dd80c6849ce4bde83470ec89b3aec67", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281119+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497920+00:00", "framework": "vllm-customized", "intentId": "5b05e0b5a4a2430ba883700a9b00e819", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281115+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497861+00:00", "framework": "vllm-customized", "intentId": "44492baee8e64456a47c47c62b317921", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281112+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497803+00:00", "framework": "vllm-customized", "intentId": "277d46a45e504fd0bb36cbf5d3a207f8", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281109+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497744+00:00", "framework": "vllm-customized", "intentId": "f5a6848026084d4abde94655ea3d6ee8", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "duplicate", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281106+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497685+00:00", "framework": "vllm-customized", "intentId": "a2e7bdd7b48b4cc289341d664a2d4369", "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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281102+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497612+00:00", "framework": "vllm-customized", "intentId": "6a9a63b578894b6aaaa31b2a79a803e8", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x8", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281099+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497517+00:00", "framework": "vllm-customized", "intentId": "697ff365f2ad40ed831c8ca4be8e4675", "repoId": "neuralmagic/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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281095+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497449+00:00", "framework": "vllm-customized", "intentId": "ea47fbbb9a8f47dbbca6626d4ada41ae", "repoId": "neuralmagic/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": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281091+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497403+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e44169b51f914ee6900fa2a1fdc19b1e", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} +{"batchId": "b053643791784de79f017488ac83d21b", "completedAt": "2026-09-21T17:22:42.281074+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:17:43.497295+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f2af51898f2d422fabed410da78a0b34", "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": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427659+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706637+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cf15f0ee588d46bdbb77e0e59a2c0173", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427657+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706598+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5f79ce7b0571469f9fbef2d120b6ef32", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "d9e266c8351d4601ac98989cd6bfec66", "completedAt": "2026-09-21T17:17:42.427650+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T17:03:14.706464+00:00", "framework": "vllm", "intentId": "82c77e22874947e2b3662acb4a2496d0", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} @@ -2462,27 +2462,3 @@ {"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969757+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f4387aea625b4501b3e1b7345465b688", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969755+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5753118d83274f9883043d8a85d69b99", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969752+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620661+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6bf33d93784240a2a1f049aadecf3340", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969749+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620619+00:00", "framework": "vllm_fix_tokenizer", "intentId": "82c73b285a7d4dbcb074c4a658e4903d", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969747+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620576+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce66ff013b784885a6d57f7a83a898ab", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969744+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620534+00:00", "framework": "vllm_fix_tokenizer", "intentId": "167a9f31f1c3434b88ee9d6a2fb741be", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969742+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620492+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ba165af4b794ddda3382fbb2dfcd603", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969740+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620449+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5cbd9985b794e77904fd1cb321859b6", "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": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969737+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620407+00:00", "framework": "vllm_fix_tokenizer", "intentId": "44943165eaca4387b18b8bf073f5ee6b", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969735+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620364+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1f27373d603e4f91a3c1d4c8bf63b025", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969732+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620321+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fdf2eb2aa10540ae9a12c16cb68ac53b", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969729+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620269+00:00", "framework": "vllm", "intentId": "fdd867715aa842069ec7529029155e48", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969723+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620177+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec29c013ec984c0899f46860f3464d55", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969719+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620136+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c9aa72d66194047bb8b750acc9149cb", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "ad8ab5660524481c98b596ffb60ebb2d", "completedAt": "2026-09-21T15:48:37.969705+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T15:36:50.620034+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80dac7b6f6cb49279fb29f8f6aa5175b", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560500+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651513+00:00", "framework": "vllm", "intentId": "6de6e0ac88b545bf9483d93dbed8b284", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560497+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651456+00:00", "framework": "vllm", "intentId": "805ac1abf9784788b971d3510068a82c", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560494+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651398+00:00", "framework": "vllm", "intentId": "fdaf04ba752c4067b0e318b0f05a99aa", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560491+00:00", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651346+00:00", "framework": "vllm-customized", "intentId": "18bcf5959f4d4217811973b43ef7d966", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} -{"batchId": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560488+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651293+00:00", "framework": "vllm-customized", "intentId": "2be69d2fcef844289ea32e687716048b", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560485+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651241+00:00", "framework": "vllm-customized", "intentId": "9180a4bbf212485983fbfa689a4f5bd7", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560482+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651188+00:00", "framework": "vllm-customized", "intentId": "4737844cbd6b4159aa96ca97f56ee4bb", "repoId": "TokenRhythm/NeoHorse-1-9B", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560479+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651134+00:00", "framework": "vllm-customized", "intentId": "c263a688375b44ada89eb5be85ca9b4c", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560476+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651080+00:00", "framework": "vllm-customized", "intentId": "15f45ba703fc4935bff4f809d10cff4d", "repoId": "XHToken/Spark-X2.5-1.7B", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560473+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.651021+00:00", "framework": "vllm-customized", "intentId": "733a1c370931484f9e8597ce1787d61b", "repoId": "TokenRhythm/NeoHorse-1-4B", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560470+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.650964+00:00", "framework": "vllm-customized", "intentId": "1358c7d8febc483782b5c7a1bbb11b6b", "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": "1673da162ed64eeca7c55b087d923643", "completedAt": "2026-09-21T14:59:12.560468+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:55:53.650906+00:00", "framework": "vllm-customized", "intentId": "304540c99a2c484e984a1765f0d2b73b", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index d77358a412..92088d3f03 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2300 + "unified_success_first": 2301 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-customized": 6, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 89, "text-generation|Cambricon_mlu-370-x8|vllm": 55, - "text-generation|Cambricon_mlu-370-x8|vllm-customized": 69, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 70, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97, "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": 134 }, - "acceptedSinceRefresh": 2300, - "acceptedTotal": 2300, - "generatedAt": "2026-09-21T17:17:42.313372+00:00", + "acceptedSinceRefresh": 2301, + "acceptedTotal": 2301, + "generatedAt": "2026-09-21T17:22:42.217393+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 7a439801fd..40939fbb15 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1013,7 +1013,6 @@ {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "modelId": "nm-testing/nonuniform", "submitTime": "2026-09-21T16:28:23.621387+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5003752", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "modelId": "pfnet/plamo-3-nict-8b-base", "submitTime": "2026-09-21T16:28:23.653856+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003786", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "submitTime": "2026-09-21T16:50:25.196591+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5004126", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.736283+00:00", "targetGpu": "Biren_166m", "taskId": "4986620", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T19:48:14.739365+00:00", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T19:48:14.745647+00:00", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T19:48:14.804006+00:00", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} @@ -1228,3 +1227,4 @@ {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "submitTime": "2026-09-21T17:11:56.354232+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5004581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index f410a328a5..712f16490e 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "0ad8bae3fa1afa7ca210869b402afc058a903fdc4e2d86ace5dcbd51a06fabd1", ".modelhub_state/recent_outcomes.jsonl": "83bd983fad4dcc2445260f494f0bf45bfd2556d0a3fc4018461652c2fa833146", ".modelhub_state/recovery_active_tasks.jsonl": "927a06881668f2ead2d5e4b131f9012e429bd8439b5820e7b3ddb4531ce28e17", - ".modelhub_state/recovery_intents.jsonl": "fc2fbbb50f64c1ec4761fa1eb536ccae8c7f8ff300f8843a45c6d52bc16ae1fb", - ".modelhub_state/routing_intelligence.json": "be65a760cfb54a679f1ae2e7b2f09f057780a223ed173756705988a02c87c882", + ".modelhub_state/recovery_intents.jsonl": "72e6dbcdbb97896e79b63425cbfcfd655fc1b71e965bfed1787c8b8a0896a9eb", + ".modelhub_state/routing_intelligence.json": "7c9ce6f6347827ab936b32b7702acc215cfae6e2b09d1165331fc9593cfc3cd0", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "2edf8b508519a3877ec20a4f6e34a897d9d87cf9dbafb3391e3eb93885538cbd", - "outcomes/submissions.jsonl": "204f5bdeb581403d3317bb0773acadcfa7ac399aff2b0ff1aa0e92a3a16bd7ad" + "ledger/submissions.jsonl": "35ad8d0eaa18cb6c57b328d1d03c0c15d984b4042970ff39e1f87ab2305b3d29", + "outcomes/submissions.jsonl": "74f2f4d8e75cee4dffc12c9fbcd32805d55c07ffa3cd59aa4a932202bf505b2c" }, - "generation": 11574, - "phase": "intent", + "generation": 11575, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T17:17:43.647643+00:00", + "updatedAt": "2026-09-21T17:22:42.433228+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index dd555c801d..f1dce826e7 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1154,3 +1154,4 @@ {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:11:56.354232+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5004581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:32.848203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5004582", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:14:33.065595+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5004583", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175161, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "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", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T15:02:24.876374+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 2018175161}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T17:17:44.806635+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5004694", "taskType": "text-generation", "verifyResult": null}