diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 58173797a..17f5fe644 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1807,50 +1807,50 @@ {"batchId": "cd7e8ec006ed4518b2c7bbea62e578e7", "completedAt": "2026-09-20T20:09:24.578631+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:09:22.950385+00:00", "framework": "transformers", "intentId": "9b1e75d077514f818695965b3dcf3333", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-20T20:29:05.906440+00:00", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation"} {"batchId": "cd7e8ec006ed4518b2c7bbea62e578e7", "completedAt": "2026-09-20T20:09:24.578639+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:09:22.950568+00:00", "framework": "transformers", "intentId": "91f04ef9a08944d2b0fb04599a84b5f5", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "reconciledAt": "2026-09-20T20:29:05.907659+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-100", "taskId": "4986875", "taskType": "text-generation"} {"batchId": "31f200a90e414acd9d89d87d10b9f188", "completedAt": "2026-09-20T20:25:24.374760+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:21:15.475639+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9964446d248b488b9d25026ba1423aa8", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "reason": null, "reconciledAt": "2026-09-20T20:29:05.906181+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4987023", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420835+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f023c7e3d24041d0b1e7abe2ce0ee3b6", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "71030a31c75341b3ad6159b64abb50ac", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420967+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ad2023a57e2d44a8a0328e770a1f90c5", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421006+00:00", "framework": "vllm", "intentId": "72f4c9fd23604ae8a8b278ee6c8b85e7", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421070+00:00", "framework": "vllm", "intentId": "2b7aedbabda64e618388bf37fe4b4863", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421129+00:00", "framework": "vllm", "intentId": "2dd9fb21e9f74d60842b164051c3e79a", "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": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421187+00:00", "framework": "vllm", "intentId": "3bf73ae5ebc84e249b9818807ec9d291", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421245+00:00", "framework": "vllm", "intentId": "9cc51955b8e240c7999ea37f06dad50f", "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": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421303+00:00", "framework": "vllm", "intentId": "a559c270db9a4d1ebbcc2fcff27cd750", "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, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421360+00:00", "framework": "vllm", "intentId": "8daf557bb56f4b4b9570822f45c1097d", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421417+00:00", "framework": "vllm", "intentId": "a3f32d9d15694a51b26ef0b9ebeaebae", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421474+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e275ed0dbae44af0b0bdf711de3e74a6", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f773d427f5e6457d949b552c822dda7d", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b64efce6cd1c47a4a4c4ff847c8f6d7d", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421605+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0e21a6e5ed34e818b2f08907ac34d31", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421648+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d666b4eef5b465abb52f66eb95783ef", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421709+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9dfc9f1111f4222b3b0c9a16e059abd", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421752+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98eb1c5b735c46d28355f4bdd1fd0f85", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421795+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dcd8a1cbf5e84d55990f8e130978e2c5", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421837+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c96c1664bff34dc3b1baef108e61d228", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421880+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3e8aaa60cd4d4a9dbc694e4a33201772", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421923+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d0d78c48a474480aefcbde11ce48e83", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421966+00:00", "framework": "vllm_fix_tokenizer", "intentId": "46d2356843a84d5d8969880b2478f3d1", "lastModified": "2026-09-10T05:36:14+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422009+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bdb63b3f4d6a461fab91c18a80133389", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422053+00:00", "framework": "vllm_fix_tokenizer", "intentId": "282b69c5c96d438a9dc9c02d878bd1a6", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422096+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0836b8b4cff34705b44964474e71ead6", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422139+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f2a1b5d667644cde8d05e11c7f6d9a32", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422182+00:00", "framework": "vllm_fix_tokenizer", "intentId": "726fcde68fe9407581fccb0c47db154f", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422225+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d2da3b9453b145dab9190b701f9aece8", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422268+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2da44aa30af34a89a1b04939605f14a1", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422311+00:00", "framework": "vllm_fix_tokenizer", "intentId": "64b2dea56d4a44d0aef09c7be86d6580", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422353+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06097effed404685b05190bfe516a957", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422397+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0d113065fac408198810cb6a41cf997", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422440+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7d9d2c7ac314c3b8d87ba3c795c5fe8", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422483+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b8d03c8b1264014987e80e11b6084f5", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa764dcccc7d458aa6215f677248eb0b", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3ce86e0110f9478cabc7fef48d5b1d85", "lastModified": "2026-09-01T03:45:04+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "56983dbc915f44939bc6b1768ce22854", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422654+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fc5a880271d5404581bb2379499387b0", "lastModified": "2026-09-03T18:32:29+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422708+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d80097b811b3488796cea626b0ab9ff9", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422751+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b043832b72e24445aa95752329348017", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422793+00:00", "framework": "vllm_fix_tokenizer", "intentId": "84935308519d4dfd93f18c430ae0b6f2", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422835+00:00", "framework": "vllm_fix_tokenizer", "intentId": "df57546ab48b47d187d5e95e7624e34f", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422877+00:00", "framework": "vllm_fix_tokenizer", "intentId": "50cf584e00f444fca1dddd48d1dafb4d", "lastModified": "2026-09-03T06:52:45+00:00", "modelAddress": "https://modelscope.cn/models/bharatgenai/Param2-17B-A2.4B-Thinking", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784120+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421187+00:00", "framework": "vllm", "intentId": "3bf73ae5ebc84e249b9818807ec9d291", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "reason": null, "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4987155", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784125+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421245+00:00", "framework": "vllm", "intentId": "9cc51955b8e240c7999ea37f06dad50f", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "reason": null, "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4987156", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784156+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421648+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d666b4eef5b465abb52f66eb95783ef", "lastModified": "2026-08-24T20:25:10+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784167+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421795+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dcd8a1cbf5e84d55990f8e130978e2c5", "lastModified": "2026-08-24T20:38:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4987185", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784213+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422311+00:00", "framework": "vllm_fix_tokenizer", "intentId": "64b2dea56d4a44d0aef09c7be86d6580", "lastModified": "2026-08-26T17:20:09+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784217+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422353+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06097effed404685b05190bfe516a957", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784262+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422877+00:00", "framework": "vllm_fix_tokenizer", "intentId": "50cf584e00f444fca1dddd48d1dafb4d", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784258+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422835+00:00", "framework": "vllm_fix_tokenizer", "intentId": "df57546ab48b47d187d5e95e7624e34f", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784254+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422793+00:00", "framework": "vllm_fix_tokenizer", "intentId": "84935308519d4dfd93f18c430ae0b6f2", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784250+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422751+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b043832b72e24445aa95752329348017", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784246+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422708+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d80097b811b3488796cea626b0ab9ff9", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784243+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422654+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fc5a880271d5404581bb2379499387b0", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784238+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "56983dbc915f44939bc6b1768ce22854", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784235+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3ce86e0110f9478cabc7fef48d5b1d85", "repoId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784231+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa764dcccc7d458aa6215f677248eb0b", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784228+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422483+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b8d03c8b1264014987e80e11b6084f5", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784224+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422440+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7d9d2c7ac314c3b8d87ba3c795c5fe8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784220+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422397+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0d113065fac408198810cb6a41cf997", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784209+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422268+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2da44aa30af34a89a1b04939605f14a1", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784206+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422225+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d2da3b9453b145dab9190b701f9aece8", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784202+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422182+00:00", "framework": "vllm_fix_tokenizer", "intentId": "726fcde68fe9407581fccb0c47db154f", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784197+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422139+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f2a1b5d667644cde8d05e11c7f6d9a32", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784193+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422096+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0836b8b4cff34705b44964474e71ead6", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784190+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422053+00:00", "framework": "vllm_fix_tokenizer", "intentId": "282b69c5c96d438a9dc9c02d878bd1a6", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784186+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.422009+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bdb63b3f4d6a461fab91c18a80133389", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784182+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421966+00:00", "framework": "vllm_fix_tokenizer", "intentId": "46d2356843a84d5d8969880b2478f3d1", "repoId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784178+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421923+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9d0d78c48a474480aefcbde11ce48e83", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784174+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421880+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3e8aaa60cd4d4a9dbc694e4a33201772", "repoId": "primitive-ai/Nex-N2.5-mini-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784171+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421837+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c96c1664bff34dc3b1baef108e61d228", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784163+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421752+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98eb1c5b735c46d28355f4bdd1fd0f85", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784159+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421709+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9dfc9f1111f4222b3b0c9a16e059abd", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784152+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421605+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b0e21a6e5ed34e818b2f08907ac34d31", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784149+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421561+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b64efce6cd1c47a4a4c4ff847c8f6d7d", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784144+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f773d427f5e6457d949b552c822dda7d", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784141+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421474+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e275ed0dbae44af0b0bdf711de3e74a6", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784136+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421417+00:00", "framework": "vllm", "intentId": "a3f32d9d15694a51b26ef0b9ebeaebae", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784132+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421360+00:00", "framework": "vllm", "intentId": "8daf557bb56f4b4b9570822f45c1097d", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784129+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421303+00:00", "framework": "vllm", "intentId": "a559c270db9a4d1ebbcc2fcff27cd750", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784116+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421129+00:00", "framework": "vllm", "intentId": "2dd9fb21e9f74d60842b164051c3e79a", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784112+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421070+00:00", "framework": "vllm", "intentId": "2b7aedbabda64e618388bf37fe4b4863", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784108+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.421006+00:00", "framework": "vllm", "intentId": "72f4c9fd23604ae8a8b278ee6c8b85e7", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784103+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420967+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ad2023a57e2d44a8a0328e770a1f90c5", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784098+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "71030a31c75341b3ad6159b64abb50ac", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} +{"batchId": "3b7a7a5670194e7dbd0d49bbadf66b69", "completedAt": "2026-09-20T20:39:10.784077+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:32:53.420835+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f023c7e3d24041d0b1e7abe2ce0ee3b6", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "3fc7c99051d54783b64f74f93eb07919", "completedAt": "2026-09-20T20:29:40.947554+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:29:30.045376+00:00", "framework": "transformers", "intentId": "16d3585502a34fd3b5b1a682ec235afa", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"} {"batchId": "3fc7c99051d54783b64f74f93eb07919", "completedAt": "2026-09-20T20:29:40.947551+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:29:30.045307+00:00", "framework": "transformers", "intentId": "01a37b75eb2c4b12b827b53fc0bb6704", "repoId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"} {"batchId": "3fc7c99051d54783b64f74f93eb07919", "completedAt": "2026-09-20T20:29:40.947548+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:29:30.045244+00:00", "framework": "transformers", "intentId": "285cd48ecb6e4e50bc33c850162f1554", "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"} @@ -2113,41 +2113,3 @@ {"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040263+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.064174+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1e31316b6ea8472d9a7581d366618652", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040260+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.064132+00:00", "framework": "vllm-patch-tokenizer", "intentId": "11c5587120d747e6b9d1662c9cba0077", "repoId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040258+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.064088+00:00", "framework": "vllm-patch-tokenizer", "intentId": "28510c6ff53044c5a26810bd3d3f188e", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040255+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.064045+00:00", "framework": "vllm-patch-tokenizer", "intentId": "1ba80cc98a87474c8b96062e0074ea35", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040252+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.064001+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b08d4e2fc0864da0a09fb241a99ba135", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040249+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063957+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9e03e076bc444e9fbb1c41bf38df4b86", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040247+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063913+00:00", "framework": "vllm-patch-tokenizer", "intentId": "75e776c569a74ddca8824fa31c858764", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040245+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063869+00:00", "framework": "vllm-patch-tokenizer", "intentId": "55f652f712d444b5a796a9a807a86a58", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040242+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063826+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9b0f86ce577b4d289a66c7ec5b80535f", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040239+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063783+00:00", "framework": "vllm-patch-tokenizer", "intentId": "8cd24564557b4c4a90887db24b99884b", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040236+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063739+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e7af58cbc4d04f3f8600e61c98bc9638", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040234+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063693+00:00", "framework": "vllm-patch-tokenizer", "intentId": "44586768fee542e5a3f3c864a451a660", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040231+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063625+00:00", "framework": "vllm-patch-tokenizer", "intentId": "56ac5aa0834a40e7b82d34bbe8f08b79", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040228+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063581+00:00", "framework": "vllm-patch-tokenizer", "intentId": "99c424cf833c486ea98b16a9ccc6d4d0", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040225+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c0eb4ca8dc934c84b55bce3a7f7ea35c", "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": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040223+00:00", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063494+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9f8857efc76a4c2fb15d8267c7b8335a", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040220+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063450+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e596cc90ca5847709926df7fccd2d5df", "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": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040217+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063406+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6fcd1cc8bd74402aa1afdfff26229069", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040214+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a80fa1ba7df14af7a19076305544958e", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040211+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063317+00:00", "framework": "vllm_fix_tokenizer", "intentId": "65e708e0964448e4877ea28ee4cc9466", "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": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040208+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063272+00:00", "framework": "vllm_fix_tokenizer", "intentId": "395de2148d524c2b8215463bc467d425", "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": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040205+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063211+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2a0a3d286b1a4c9d8fd7817431d2b720", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040202+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063120+00:00", "framework": "vllm", "intentId": "fa37845d2ff1478582e74b8e894846ca", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040199+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.063024+00:00", "framework": "vllm", "intentId": "bb9f8d2ca7b546ccbd6136ee559ddcc5", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040197+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062931+00:00", "framework": "vllm", "intentId": "f7edbbec5eb94dff9a4c0fc4ec2fc564", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "age_policy_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040193+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062834+00:00", "framework": "vllm", "intentId": "5e5bd3ed7e9547a38a2901c907cd5944", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040191+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062735+00:00", "framework": "vllm", "intentId": "b8ef7c41929549089cfa0ba36fc44cc5", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040188+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062624+00:00", "framework": "vllm", "intentId": "6a4c12087e2f4a9b991dd346d5151a03", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040185+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062520+00:00", "framework": "vllm", "intentId": "4859e41aa6934b6a9179bcca734eef54", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040182+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062416+00:00", "framework": "vllm", "intentId": "a703f2b63928431190139c54cd3597fe", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040179+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062309+00:00", "framework": "vllm", "intentId": "8dc9d0879aa0436cb4639d4475fedc9f", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040176+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062215+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5a9f3c58897845a79d7d770f9525acf4", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040172+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062147+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d89adce690fe4215a296d83d810e52a8", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040169+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062080+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e417205a2e44be39cfb239986211810", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040166+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.062011+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0b18b4cf7b0143ba97e6f76a4dc74c40", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040163+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061940+00:00", "framework": "vllm_tokenizer_patch", "intentId": "29e3fb487628490e8075797386e6c132", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040160+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061871+00:00", "framework": "vllm_tokenizer_patch", "intentId": "24a05fb6a76c4c269554367548a51da8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040156+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061801+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4daca9a53c164d6a998a4e8b712a2ca3", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "627b79e82e5d44d8809a85cc9fbe8757", "completedAt": "2026-09-20T19:44:35.040149+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:37:07.061724+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7855770a6b624b93b5c0bd599339466d", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} -{"batchId": "91968e61747d4364bdf7fbbd10ba49db", "completedAt": "2026-09-20T19:33:29.660610+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:30:13.722836+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa97881dc8e3454ebec11fb6594b1844", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} -{"batchId": "91968e61747d4364bdf7fbbd10ba49db", "completedAt": "2026-09-20T19:33:29.660607+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T19:30:13.722782+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79fcf9866bbe4c3783524c9a26364fdb", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 2af1fa4ff..4670a30b5 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1947 + "unified_success_first": 1953 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -10,7 +10,7 @@ "text-generation|Ascend_910-b4|vllm": 20, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 130, "text-generation|Biren_166m|vllm": 79, - "text-generation|Biren_166m|vllm_fix_tokenizer": 40, + "text-generation|Biren_166m|vllm_fix_tokenizer": 44, "text-generation|Cambricon_mlu-370-x4|vllm": 50, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 82, @@ -25,7 +25,7 @@ "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 39, "text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 3, "text-generation|Iluvatar_mrv-100|vllm": 61, - "text-generation|Kunlunxin_p-800|vllm": 20, + "text-generation|Kunlunxin_p-800|vllm": 22, "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 175, "text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 70, "text-generation|MetaX_c-500|vllm": 104, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 113 }, - "acceptedSinceRefresh": 1947, - "acceptedTotal": 1947, - "generatedAt": "2026-09-20T20:29:40.887244+00:00", + "acceptedSinceRefresh": 1953, + "acceptedTotal": 1953, + "generatedAt": "2026-09-20T20:39:10.719911+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 10fa70133..4d7427598 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1139,3 +1139,9 @@ {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "submitTime": "2026-09-20T14:26:11.835960+00:00", "targetGpu": "Biren_166m", "taskId": "4980425", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T14:26:18.189644+00:00", "targetGpu": "Biren_166m", "taskId": "4980427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T19:28:11.202603+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4986310", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-20T20:33:04.562192+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987155", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-20T20:33:04.573215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987156", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-20T20:33:30.958684+00:00", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T20:33:46.481514+00:00", "targetGpu": "Biren_166m", "taskId": "4987185", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "submitTime": "2026-09-20T20:35:36.652541+00:00", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} +{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} diff --git a/manifest.json b/manifest.json index 830dcf062..48cce6057 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "1b3fa1aa58f01be333943273e5b1ae4b006293bf468ef8f45785c28ad126b65c", ".modelhub_state/recent_outcomes.jsonl": "ba8532b51ae92ae7178588826957996e9ddb45571ff4b43e54c57741df0efa6d", ".modelhub_state/recovery_active_tasks.jsonl": "6e1d980d56f45e9684a72b3dafecca7b3e45af5f941f57312ca17d58a2378b1e", - ".modelhub_state/recovery_intents.jsonl": "a36b91685a1c450089f37e82c63a3b6e8946fa6db242c7ed8d4ca97577404e97", - ".modelhub_state/routing_intelligence.json": "6406083fb4fd9a2c2394fac8ab24bda7fd56bac628a824b35e517934dfc13b3b", + ".modelhub_state/recovery_intents.jsonl": "f500980f978f564c1f691a012f9588f24554ba152aa7269e82e0b3458da86f3a", + ".modelhub_state/routing_intelligence.json": "6728396f79f936b040c8d749a74e8ae464fb702d71671ce44045060fa65259fb", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "0f724d35803bb909bcb72146360ddde84dafd6eb79bd3a15b525cd977538dacd", - "outcomes/submissions.jsonl": "dcd83e3ca3a4b0c7bc60568cce8592eea462ff87745cabb6d8bfbd5126fa11ec" + "ledger/submissions.jsonl": "73e88a5f86e7d25dc59a9df42016a9f0eef60db7cd174fdafcde76c53d4cac5e", + "outcomes/submissions.jsonl": "a346e4fca2855962f451b777819b64f9e895cb351f14a2def2b6119a95d35e03" }, - "generation": 10896, - "phase": "intent", + "generation": 10897, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T20:32:53.609714+00:00", + "updatedAt": "2026-09-20T20:39:10.977203+00:00", "writerId": "fc715c06e24c4db2ae3e425e435db996" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 5b31e558b..cb147edcb 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1106,3 +1106,9 @@ {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:09:24.460163+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986875", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:21:26.745613+00:00", "targetGpu": "Biren_166m", "taskId": "4987023", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:33:04.562192+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987155", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:33:04.573215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987156", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:33:30.958684+00:00", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:33:46.481514+00:00", "targetGpu": "Biren_166m", "taskId": "4987185", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:35:36.652541+00:00", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "verifyResult": null}