CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 11559 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 16:49:29 +00:00
parent 1f319a60ba
commit 329e01fc1f
3 changed files with 29 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
.modelhub_state/recovery_intents.jsonl
View File

@@ -2148,29 +2148,29 @@
{"batchId": "1d7f222438574c7bb7d308b0b6ff99a2", "completedAt": "2026-09-21T16:21:12.536989+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:20:53.320004+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d51a43dc8a934b9d82753d02071dfdf1", "lastModified": "2026-09-21T15:48:16+00:00", "modelAddress": "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "reason": null, "reconciledAt": "2026-09-21T16:25:07.971039+00:00", "repoId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation"}
{"batchId": "820eee67f37e4f75b88ed9ffc43ae8b4", "completedAt": "2026-09-21T16:43:19.662893+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:28:02.227691+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fe4f5021d5e5486f84ed19784d4bf60c", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "reason": null, "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "5003752", "taskType": "text-generation"}
{"batchId": "820eee67f37e4f75b88ed9ffc43ae8b4", "completedAt": "2026-09-21T16:43:19.662910+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:28:02.227920+00:00", "framework": "vllm", "intentId": "99ca3a53cef64e7fbd321817525860cf", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "reason": null, "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "5003786", "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498132+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97d1a2970a894e52923ae00f4a3a11b8", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498231+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5258b2ff88674ccdbd59e33f5c6275fe", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498276+00:00", "framework": "vllm-customized", "intentId": "bd005c7007cb4163b962acc873005c1b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498343+00:00", "framework": "vllm-customized", "intentId": "aa14e7743e4244dd852141177dc23540", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498404+00:00", "framework": "vllm-customized", "intentId": "edc310580c944d0ba2321ec75d1be342", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498463+00:00", "framework": "vllm-customized", "intentId": "cc6eaa4744654a4bbab9fa56c9b8a90b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498522+00:00", "framework": "vllm-customized", "intentId": "437d65d2ba03402a8a3f91a9fa4b2bd5", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498580+00:00", "framework": "vllm-customized", "intentId": "71dd60019ebc4496b7755a246fe0cd8f", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498640+00:00", "framework": "vllm-customized", "intentId": "00bcff43cab3483391b681dd7bf2d4de", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498715+00:00", "framework": "vllm-customized", "intentId": "915e0716b2564a01980d6fbf444f3506", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498773+00:00", "framework": "vllm-customized", "intentId": "d9f0d6ddba4f41c190d9475af822611e", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498831+00:00", "framework": "vllm-customized", "intentId": "fd9877836dfa489494b11347ce1b70d3", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498890+00:00", "framework": "vllm-customized", "intentId": "b5a8be2e3bae478facf78e622ddcef6b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498947+00:00", "framework": "vllm-customized", "intentId": "effef78088474a31a63a1280c01c93a8", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499005+00:00", "framework": "vllm-customized", "intentId": "3de7bc3b32db426aada1229a46846123", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499062+00:00", "framework": "vllm-customized", "intentId": "a1aa1b9e709b4cbbb0f6a870d538425d", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499121+00:00", "framework": "vllm-customized", "intentId": "b9684a06db5145a3b0191b55f886f3f4", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499175+00:00", "framework": "vllm-customized", "intentId": "cb67a1f5054644b78fadde766f89a5ce", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499229+00:00", "framework": "vllm-customized", "intentId": "de5427a0832147f8a74c69628889ee33", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499282+00:00", "framework": "vllm-customized", "intentId": "8a0c4329af36406da6ab88de5f1c25f8", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499334+00:00", "framework": "vllm-customized", "intentId": "4c8bd7a1a75549238b40ff2a1d67058e", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499386+00:00", "framework": "vllm", "intentId": "9d05978022d44ed698385ac07fc114b9", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499444+00:00", "framework": "vllm", "intentId": "dbf6555cb7f7401f8f153cc8ee23c45f", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512236+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499444+00:00", "framework": "vllm", "intentId": "dbf6555cb7f7401f8f153cc8ee23c45f", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512233+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499386+00:00", "framework": "vllm", "intentId": "9d05978022d44ed698385ac07fc114b9", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512230+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499334+00:00", "framework": "vllm-customized", "intentId": "4c8bd7a1a75549238b40ff2a1d67058e", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512227+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499282+00:00", "framework": "vllm-customized", "intentId": "8a0c4329af36406da6ab88de5f1c25f8", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512224+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499229+00:00", "framework": "vllm-customized", "intentId": "de5427a0832147f8a74c69628889ee33", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512222+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499175+00:00", "framework": "vllm-customized", "intentId": "cb67a1f5054644b78fadde766f89a5ce", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512219+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499121+00:00", "framework": "vllm-customized", "intentId": "b9684a06db5145a3b0191b55f886f3f4", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512216+00:00", "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499062+00:00", "framework": "vllm-customized", "intentId": "a1aa1b9e709b4cbbb0f6a870d538425d", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512213+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.499005+00:00", "framework": "vllm-customized", "intentId": "3de7bc3b32db426aada1229a46846123", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512210+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498947+00:00", "framework": "vllm-customized", "intentId": "effef78088474a31a63a1280c01c93a8", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512207+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498890+00:00", "framework": "vllm-customized", "intentId": "b5a8be2e3bae478facf78e622ddcef6b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512204+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498831+00:00", "framework": "vllm-customized", "intentId": "fd9877836dfa489494b11347ce1b70d3", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512201+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498773+00:00", "framework": "vllm-customized", "intentId": "d9f0d6ddba4f41c190d9475af822611e", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512198+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498715+00:00", "framework": "vllm-customized", "intentId": "915e0716b2564a01980d6fbf444f3506", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512195+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498640+00:00", "framework": "vllm-customized", "intentId": "00bcff43cab3483391b681dd7bf2d4de", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512193+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498580+00:00", "framework": "vllm-customized", "intentId": "71dd60019ebc4496b7755a246fe0cd8f", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512190+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498522+00:00", "framework": "vllm-customized", "intentId": "437d65d2ba03402a8a3f91a9fa4b2bd5", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512187+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498463+00:00", "framework": "vllm-customized", "intentId": "cc6eaa4744654a4bbab9fa56c9b8a90b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512184+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498404+00:00", "framework": "vllm-customized", "intentId": "edc310580c944d0ba2321ec75d1be342", "repoId": "neuralmagic/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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512180+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498343+00:00", "framework": "vllm-customized", "intentId": "aa14e7743e4244dd852141177dc23540", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512177+00:00", "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498276+00:00", "framework": "vllm-customized", "intentId": "bd005c7007cb4163b962acc873005c1b", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512173+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498231+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5258b2ff88674ccdbd59e33f5c6275fe", "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": "c3d20cada40b40b5b8f6ae2e5af009fd", "completedAt": "2026-09-21T16:49:29.512158+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:43:23.498132+00:00", "framework": "vllm_tokenizer_patch", "intentId": "97d1a2970a894e52923ae00f4a3a11b8", "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": "820eee67f37e4f75b88ed9ffc43ae8b4", "completedAt": "2026-09-21T16:43:19.663078+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:28:02.230393+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80af97508a2442fb8c9237f02678295d", "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": "820eee67f37e4f75b88ed9ffc43ae8b4", "completedAt": "2026-09-21T16:43:19.663076+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:28:02.230352+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d2a717d1fad40ed84a1e04cc408acb7", "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": "820eee67f37e4f75b88ed9ffc43ae8b4", "completedAt": "2026-09-21T16:43:19.663072+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T16:28:02.230305+00:00", "framework": "vllm", "intentId": "3fd29aa68e564ca08fafa809e6c2a9cb", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "age_policy_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
@@ -2448,26 +2448,3 @@
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786622+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163836+00:00", "framework": "transformers", "intentId": "f77ccf3fef054cf6862655d7a587cdaa", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786619+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163774+00:00", "framework": "transformers", "intentId": "d7e15ca7b8c44995a39e6f48945dc111", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786617+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1b9e29c9993f422faa0ae11abc424453", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786614+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163689+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bb0faa1e2b3148cf975cb37e5ebd12d6", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786612+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163641+00:00", "framework": "vllm_fix_tokenizer", "intentId": "14de06302c184eda996eae0a0193833a", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786609+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163599+00:00", "framework": "vllm_fix_tokenizer", "intentId": "abc2aa54438e4a299d933c30053890e1", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786606+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163556+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a53fec18ec554abcac60618adcb30cbc", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786604+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163513+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5c891cb7f72049b29411298f49a68a5a", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786601+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163470+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea527c7887674eb485c5df4e17d96026", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786599+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163428+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba26cb0d1a9b47eda4f6840bbc6c6694", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786596+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163384+00:00", "framework": "vllm_fix_tokenizer", "intentId": "67b26970726548b5b79fa31063f1da91", "repoId": "RedHatAI/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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786593+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163340+00:00", "framework": "vllm_fix_tokenizer", "intentId": "77bb580cd3264012a82186f52befbdc8", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786591+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163297+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bfbcf377c8a243cf8927714e79e5ae98", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786588+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163254+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ca636561f7534aafb49eab32211a423a", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786586+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163210+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc55b4cd10f94f6b8bd5a41bdeb594df", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786583+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163167+00:00", "framework": "vllm_fix_tokenizer", "intentId": "60ecc72d180943deb6bf62adbc0662c5", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786580+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163124+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b1af2f4fd8d246a3b749ebe0d7f308b1", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786578+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163081+00:00", "framework": "vllm_fix_tokenizer", "intentId": "34c7943082724c129c27e7863a33fbe7", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786575+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.163039+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a1e807f23ce0422dbec774de07fb9b81", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786572+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162996+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e78198eacd9246d6b2e26012de7512ac", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786569+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162953+00:00", "framework": "vllm_fix_tokenizer", "intentId": "601fc9af8a7142d486f3b970aa23b8c5", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786566+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162909+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e9b80cd61297402f98ced693fa1f3bf5", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
{"batchId": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786563+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162859+00:00", "framework": "vllm", "intentId": "476fa13508124df9a1d99814bfdd3e7a", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786550+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162609+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9859d695ebe6468bb4eb10e486d0622d", "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": "068704d34956435f8dd65c7c5df93103", "completedAt": "2026-09-21T14:55:52.786540+00:00", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:48:03.162528+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5e16e0385a644276839116c786bb309f", "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": "7856f9a1debf4a6e9654fa700f4c4c04", "completedAt": "2026-09-21T14:30:18.402614+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T14:30:09.200656+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8ef81bc3133417f81dca08034415e28", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}

2
.modelhub_state/routing_intelligence.json
View File

@@ -40,6 +40,6 @@
},
"acceptedSinceRefresh": 2287,
"acceptedTotal": 2287,
"generatedAt": "2026-09-21T16:43:19.596530+00:00",
"generatedAt": "2026-09-21T16:49:29.383351+00:00",
"version": 1
}