diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 364157c941..c448acbfcc 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2104,6 +2104,37 @@ {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291967+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267848+00:00", "framework": "vllm", "intentId": "6f421226cfb54296a0542d8b0ed46b6a", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5001062", "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291970+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267906+00:00", "framework": "vllm", "intentId": "74da361d638e4e30932524ccdf826191", "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": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5001063", "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291972+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267963+00:00", "framework": "vllm", "intentId": "13bf4cfa6dfb4d309aa8f8e94b2c4168", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "reason": null, "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5001061", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198392+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8970884dc00045d09f267a48ebe189bc", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198519+00:00", "framework": "vllm", "intentId": "f0aa7c75484640c88d7b31e442b388e7", "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}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198575+00:00", "framework": "vllm", "intentId": "53f9c3a36a0a460a93721cb43e58c422", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198624+00:00", "framework": "vllm", "intentId": "ff53184ea325465f94637d6f26f1ba3e", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198679+00:00", "framework": "vllm", "intentId": "4db44869378a44869919fadf91c266c6", "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}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198728+00:00", "framework": "vllm", "intentId": "8bc152872a7742f0b2a4c41d3b984884", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198777+00:00", "framework": "vllm", "intentId": "89a22e31c6c34c769ddaf378bc3d19cb", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198824+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e793ce5635c4d0e808c7f9dbcb6b81f", "lastModified": "2026-09-10T05:31:36+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198868+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b4e485f555c84e55b986d3c6561600f4", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a0eb2705330d41638bf588a105c4553b", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198951+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d70db552a32c46149f8089c4b8c5f524", "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": {"gpuNum": 1}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.198991+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba10ea6b68a64175a7c6c223191efac5", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199032+00:00", "framework": "vllm-customized", "intentId": "63d8bec6847b49ef88c21586b7b62a18", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199095+00:00", "framework": "vllm-customized", "intentId": "0edd1c03308041e79015cf5fc0dc9d25", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199156+00:00", "framework": "vllm-customized", "intentId": "46a1e3fbc850403b944d872dc8252967", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199215+00:00", "framework": "vllm-customized", "intentId": "9819a744b1c244b2b81b58a6f52313e5", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199275+00:00", "framework": "vllm-customized", "intentId": "2ea1e21e52fe4fb2bc392c5201bfef61", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199334+00:00", "framework": "vllm-customized", "intentId": "107c66158335401fa6f32b4209dbfed7", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199392+00:00", "framework": "vllm-customized", "intentId": "c9a4296f790b4b609022fe0927cdeef9", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199451+00:00", "framework": "vllm-customized", "intentId": "19ab7845c8394d0999305985aa0302d9", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199509+00:00", "framework": "vllm-customized", "intentId": "50500fb666374309a4bb994feb2db889", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199567+00:00", "framework": "vllm-customized", "intentId": "3c80870e29ad49f088c769fea665fcdb", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199629+00:00", "framework": "vllm-customized", "intentId": "c732500d7b1041179ca3565d57072109", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199690+00:00", "framework": "vllm-customized", "intentId": "53b4587ce3724930b044af2c3016e3f8", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199745+00:00", "framework": "vllm-customized", "intentId": "be897c5fc85a4550ae7a56821ed40990", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199799+00:00", "framework": "vllm-customized", "intentId": "1318ed3a48c5499aabebaae9d007ed8e", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199854+00:00", "framework": "vllm-customized", "intentId": "702c3de29bf04987a0d9d48b1c2eae5f", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "0378395697c8345a5f2bfec5cd339a734a57d469359b2d1e41bd5325ee9d95e5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199907+00:00", "framework": "vllm-customized", "intentId": "5c1977145bed4e7d996ccbf8a59959c9", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"dtype": "auto", "gpuMemoryUtilization": 0.95, "gpuNum": 1, "maxModelLen": 2048, "tensorParallel": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199961+00:00", "framework": "vllm", "intentId": "69ca6ed0cf9747119b2d008deb762358", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.200021+00:00", "framework": "vllm", "intentId": "e0c7ac7008394ef58e4332e57fa44ec4", "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": "9cb2439dc27a4294ba6fc5cd6afe80f3", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.200080+00:00", "framework": "vllm", "intentId": "7b95fa300bf44f589a7807314d2d6cf8", "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": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.292106+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.270394+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9f0ab20b06064f7c983d72b0ab442152", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.292103+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.270352+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c1602df0622e4d399f4c88bb8c279cb0", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.292101+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.270310+00:00", "framework": "vllm-patch-tokenizer", "intentId": "4b5e97b44d714a34a60026d401f0318b", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index e8cfc246be..abce73aa45 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f056ed79dc68b93c34c77c843adbb41f111ead8321367e55fb184c2bf909b4b8", ".modelhub_state/recent_outcomes.jsonl": "547a04d8d65f244ddfe7587f83edc0672c6530bf217bc4d021930e6c200af0ac", ".modelhub_state/recovery_active_tasks.jsonl": "0c0a83999f1c20ab00be3f7434342dcf340512cca81f2003552695f3bd102b43", - ".modelhub_state/recovery_intents.jsonl": "30658c51dcb66ca7fd5e88694e0c383b37855102766c3702a5e2ab43d4a81c64", + ".modelhub_state/recovery_intents.jsonl": "d079005e1ed47060cea4535ad56133b7eb49b78cb0726f68eeec96bfb561380a", ".modelhub_state/routing_intelligence.json": "ca74dcc537a45c0bdc50968fac602c5cf7d95821253fefd8a647046f334718bb", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "c5e5261d718faa2d35908f7e8ff7d34a2656412dab397bfb88bdf9ca927562f8", "outcomes/submissions.jsonl": "c48b3e2e9bda0f81e42566f2260d79f4e169d0f4ce0c5de2bb293cc129259f4e" }, - "generation": 11459, - "phase": "result", + "generation": 11460, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T12:54:38.435817+00:00", + "updatedAt": "2026-09-21T12:54:39.350502+00:00", "writerId": "8b35139af6674067a339a670222d4b67" }