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

state: generation 10142 (result)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 03:41:49 +00:00
parent 22eda92033
commit ea277fdce2
5 changed files with 221 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

128
.modelhub_state/recovery_intents.jsonl
View File

@@ -1291,70 +1291,70 @@
{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644518+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951421+00:00", "framework": "vllm", "intentId": "b40ac99fc2644917aeba138a4ee25e2d", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T03:40:45.898699+00:00", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation"}
{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644520+00:00", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951468+00:00", "framework": "vllm", "intentId": "edb59f1232c14b8783296fa28311e566", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T03:40:45.899547+00:00", "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation"}
{"batchId": "63dd409721f8427398583e231542cb8f", "completedAt": "2026-09-20T03:40:44.644521+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:40:34.951515+00:00", "framework": "vllm", "intentId": "1185bb045aa845d1a8e8031101422f33", "lastModified": "2026-08-25T12:09:43+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "reason": null, "reconciledAt": "2026-09-20T03:40:45.900019+00:00", "repoId": "LiquidAI/LFM2.5-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.411928+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da037b274c804ed6abcb51338767b82c", "lastModified": "2026-08-24T20:23:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412045+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cdf2050bd2c640dfb9aec20e8578c0b5", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412098+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d986d503d07a43d190f7fb5e1619e742", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412148+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce5f6ca302bb4970b125da3809ca9086", "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": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412192+00:00", "framework": "vllm_fix_tokenizer", "intentId": "36a6acb29a23470581cfee17a3d8370d", "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": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412235+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6ae801a11ec54357932862e0e5833ee3", "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": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412278+00:00", "framework": "vllm_fix_tokenizer", "intentId": "afe60c7159a14dfe80a7ea78b32f597a", "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": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412320+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e9f5c9fb69344e2c86560064b1f57047", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412363+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ac53c0b60fef49a0bb89013d676b72e1", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412405+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2d14815b16749acbac808eb7d0a4786", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412447+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5a843e44a17428abab092918c373907", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412501+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c66e43feb2b4ba1ac6c12f13a6a284e", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412543+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aeccd8c5a26142acb25cabc1a50ffdfd", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6cb5f3b516c3458988540a3553e96c55", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412635+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4d2a40631b2401e8f2f97a83a8fd63b", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412688+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a877c5d6ce44028aa395291a336a8d0", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412736+00:00", "framework": "vllm_tokenizer_patch", "intentId": "82d19815d0bf4460b08af1954b304f17", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412784+00:00", "framework": "vllm_tokenizer_patch", "intentId": "20d99abf9fb543a5bc0c34cc875ec59a", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412823+00:00", "framework": "vllm-mlu", "intentId": "215fdc88a40d4bcca4f9157f7a60d4ba", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412889+00:00", "framework": "vllm", "intentId": "8438554c9f844fe9a18abb4fbf49c8f5", "lastModified": "2026-09-16T16:39:48+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "repoId": "BAAI/RoboBrain2.5-8B-MT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412947+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "3aaa8177b6224e0eb13fcf5bfafd49f2", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412992+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "0278ffe6b63a4ac399644dc8898cf580", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413048+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "39da44defea74f5081475b2231f057e5", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413092+00:00", "framework": "vllm", "intentId": "5d331b0b4adb45d2bb7f042ad18ded73", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413146+00:00", "framework": "vllm", "intentId": "339e9c54daff46469578b70bbba3c683", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413199+00:00", "framework": "vllm", "intentId": "f60bfa2f7aa545c8aa7b37a6158bec3e", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413253+00:00", "framework": "vllm", "intentId": "8fec6c0c9ccd4df3bf97186a13c7baa1", "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": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413308+00:00", "framework": "vllm", "intentId": "e4c13fd5146c442d9a47eebeecca0d4e", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413362+00:00", "framework": "vllm", "intentId": "bcb8f3901dc940c79a07b4e4163a6710", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413416+00:00", "framework": "vllm", "intentId": "04eb078ee76545efbcb4ff5867077917", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413469+00:00", "framework": "vllm", "intentId": "1c361d24696d4c4e96e490cc07d38e7b", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413517+00:00", "framework": "vllm", "intentId": "3c80a0eaba4e4ae0b006e2d0fe8d8f4e", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413565+00:00", "framework": "vllm", "intentId": "f742950881ff4c82ba687b5d06b950af", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413613+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5ab880a6066c49589cb46968f7a5639b", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413655+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5fd007c6d0ca4b1094e0f43f6f9d69ff", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413705+00:00", "framework": "vllm_fix_tokenizer", "intentId": "abb23c2cb9ef41c6bacd5094c09498a1", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413747+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3a3303fa957445d7b133d0dfe5c08ffe", "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": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413790+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0e987c5730514c6f856bdb247c7809f5", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413831+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e6b69eb67ef546aa81c6f7d0ba13b665", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413873+00:00", "framework": "transformers", "intentId": "68b6c1891a7547a789f25a80ecb39736", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413936+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ea9f44394df0405884d6dd4921c1fe5a", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413978+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9336d273de19493b9c28e6f7f74cf8bc", "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": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414020+00:00", "framework": "vllm-patch-tokenizer", "intentId": "984cbb78b2ed44e7b62797fb2a37e9fd", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414061+00:00", "framework": "vllm-patch-tokenizer", "intentId": "837a0b083d79402a8ff9089ab947c221", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414103+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2c755d1188f84158a5f1af2f439fbd4a", "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": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414145+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0607ce4c6ce24a6db50145fb69de2979", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414187+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7b90b214f26488aa737d01d1b4bb16c", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414229+00:00", "framework": "vllm-patch-tokenizer", "intentId": "79ac4416532e431ca1d10b0239a851bc", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414270+00:00", "framework": "vllm-patch-tokenizer", "intentId": "664522c0569742d7a0dc1e92d812f5c6", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414311+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ae690d6e12d0410b831ca54bc0ef7038", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414353+00:00", "framework": "vllm-patch-tokenizer", "intentId": "83a2d29587ac4481892a99108bb3e3dd", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414394+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9228f38bcfda48a1a267b095d71e761c", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414436+00:00", "framework": "vllm-patch-tokenizer", "intentId": "303974583fbe48a09e4bd24cefaf62dc", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414477+00:00", "framework": "vllm", "intentId": "fa63e7ca09c141febba0d1ae93c17a51", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414525+00:00", "framework": "vllm", "intentId": "7d4a0e14bf46430499b4e31b6a8be72d", "lastModified": "2026-08-24T20:28:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414573+00:00", "framework": "vllm", "intentId": "bc0954808f98484e8f5e5bf061aeaf63", "lastModified": "2026-08-24T20:25:20+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414620+00:00", "framework": "vllm", "intentId": "81ec521e02c6416380793c47b1d54e9d", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414673+00:00", "framework": "vllm-customized", "intentId": "b78f68a2a4ab46fb81deed30b7be615c", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414731+00:00", "framework": "vllm-customized", "intentId": "06bf50cc38064f5589f6dd3afc99bdde", "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": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414787+00:00", "framework": "vllm", "intentId": "fa32db56d72546efabf9b973efe4fcdb", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414843+00:00", "framework": "vllm", "intentId": "4ac2bcb16c4f41d6b96b7e6d08309237", "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": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414886+00:00", "framework": "vllm", "intentId": "e0ba7290bad645e0a89a5783afec2ad1", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414928+00:00", "framework": "vllm", "intentId": "5d7ccaa875f84600aed53eddb056921d", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414970+00:00", "framework": "vllm", "intentId": "7f583607a33b45738e0e1d567dd10773", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845864+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.411928+00:00", "framework": "vllm_tokenizer_patch", "intentId": "da037b274c804ed6abcb51338767b82c", "lastModified": "2026-08-24T20:23:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969989", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845877+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412045+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cdf2050bd2c640dfb9aec20e8578c0b5", "lastModified": "2026-08-24T20:23:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969991", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845881+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412098+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d986d503d07a43d190f7fb5e1619e742", "lastModified": "2026-08-24T20:22:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4969987", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845884+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412148+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce5f6ca302bb4970b125da3809ca9086", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969994", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845887+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412192+00:00", "framework": "vllm_fix_tokenizer", "intentId": "36a6acb29a23470581cfee17a3d8370d", "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": "Vastai_va16", "taskId": "4969990", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845889+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412235+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6ae801a11ec54357932862e0e5833ee3", "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": "Vastai_va16", "taskId": "4969985", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845892+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412278+00:00", "framework": "vllm_fix_tokenizer", "intentId": "afe60c7159a14dfe80a7ea78b32f597a", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969988", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845894+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412320+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e9f5c9fb69344e2c86560064b1f57047", "lastModified": "2026-09-15T15:01:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969986", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845896+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412363+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ac53c0b60fef49a0bb89013d676b72e1", "lastModified": "2026-09-17T15:15:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969992", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845899+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412405+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2d14815b16749acbac808eb7d0a4786", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969984", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845902+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412447+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e5a843e44a17428abab092918c373907", "lastModified": "2026-09-17T13:29:50+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969995", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845904+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412501+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c66e43feb2b4ba1ac6c12f13a6a284e", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Vastai_va16", "taskId": "4969993", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845907+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412543+00:00", "framework": "vllm_fix_tokenizer", "intentId": "aeccd8c5a26142acb25cabc1a50ffdfd", "lastModified": "2026-08-26T12:21:34+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4969998", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845910+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412585+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6cb5f3b516c3458988540a3553e96c55", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "reason": null, "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970005", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845913+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412635+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4d2a40631b2401e8f2f97a83a8fd63b", "lastModified": "2026-09-17T14:05:32+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970006", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845916+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412688+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a877c5d6ce44028aa395291a336a8d0", "lastModified": "2026-09-17T13:39:53+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970003", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845918+00:00", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412736+00:00", "framework": "vllm_tokenizer_patch", "intentId": "82d19815d0bf4460b08af1954b304f17", "lastModified": "2026-09-17T13:54:18+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970000", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845921+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412784+00:00", "framework": "vllm_tokenizer_patch", "intentId": "20d99abf9fb543a5bc0c34cc875ec59a", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4970002", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845924+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412823+00:00", "framework": "vllm-mlu", "intentId": "215fdc88a40d4bcca4f9157f7a60d4ba", "lastModified": "2026-09-19T14:40:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969996", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845927+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412889+00:00", "framework": "vllm", "intentId": "8438554c9f844fe9a18abb4fbf49c8f5", "lastModified": "2026-09-16T16:39:48+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-MT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4970004", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845929+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412947+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "3aaa8177b6224e0eb13fcf5bfafd49f2", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "reason": null, "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969999", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845932+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.412992+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "0278ffe6b63a4ac399644dc8898cf580", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970001", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845934+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413048+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "39da44defea74f5081475b2231f057e5", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "reason": null, "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4969997", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845937+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413092+00:00", "framework": "vllm", "intentId": "5d331b0b4adb45d2bb7f042ad18ded73", "lastModified": "2026-09-11T12:06:58+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "reason": null, "repoId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4970007", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845939+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413146+00:00", "framework": "vllm", "intentId": "339e9c54daff46469578b70bbba3c683", "lastModified": "2026-08-26T18:08:39+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845941+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413199+00:00", "framework": "vllm", "intentId": "f60bfa2f7aa545c8aa7b37a6158bec3e", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "reason": null, "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845944+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413253+00:00", "framework": "vllm", "intentId": "8fec6c0c9ccd4df3bf97186a13c7baa1", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "reason": null, "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845947+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413308+00:00", "framework": "vllm", "intentId": "e4c13fd5146c442d9a47eebeecca0d4e", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "reason": null, "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970015", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845949+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413362+00:00", "framework": "vllm", "intentId": "bcb8f3901dc940c79a07b4e4163a6710", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "reason": null, "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970016", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845951+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413416+00:00", "framework": "vllm", "intentId": "04eb078ee76545efbcb4ff5867077917", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "reason": null, "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970013", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845954+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413469+00:00", "framework": "vllm", "intentId": "1c361d24696d4c4e96e490cc07d38e7b", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "reason": null, "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970014", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845956+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413517+00:00", "framework": "vllm", "intentId": "3c80a0eaba4e4ae0b006e2d0fe8d8f4e", "lastModified": "2026-08-26T16:52:04+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "reason": null, "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970011", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845958+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413565+00:00", "framework": "vllm", "intentId": "f742950881ff4c82ba687b5d06b950af", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "reason": null, "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970009", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845961+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413613+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5ab880a6066c49589cb46968f7a5639b", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "reason": null, "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845964+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413655+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5fd007c6d0ca4b1094e0f43f6f9d69ff", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "reason": null, "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970020", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845966+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413705+00:00", "framework": "vllm_fix_tokenizer", "intentId": "abb23c2cb9ef41c6bacd5094c09498a1", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "reason": null, "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970019", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845969+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413747+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3a3303fa957445d7b133d0dfe5c08ffe", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "reason": null, "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970021", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845971+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413790+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0e987c5730514c6f856bdb247c7809f5", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "reason": null, "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970022", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845973+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413831+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e6b69eb67ef546aa81c6f7d0ba13b665", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "reason": null, "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970018", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845976+00:00", "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413873+00:00", "framework": "transformers", "intentId": "68b6c1891a7547a789f25a80ecb39736", "lastModified": "2026-08-26T16:48:25+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970023", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845979+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413936+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ea9f44394df0405884d6dd4921c1fe5a", "lastModified": "2026-08-24T20:36:30+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "reason": null, "repoId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970024", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845981+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.413978+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9336d273de19493b9c28e6f7f74cf8bc", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "reason": null, "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970026", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845984+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414020+00:00", "framework": "vllm-patch-tokenizer", "intentId": "984cbb78b2ed44e7b62797fb2a37e9fd", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970028", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845986+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414061+00:00", "framework": "vllm-patch-tokenizer", "intentId": "837a0b083d79402a8ff9089ab947c221", "lastModified": "2026-08-24T20:36:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970025", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845989+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414103+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2c755d1188f84158a5f1af2f439fbd4a", "lastModified": "2026-08-24T20:38:11+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "reason": null, "repoId": "RedHatAI/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970029", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845992+00:00", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414145+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0607ce4c6ce24a6db50145fb69de2979", "lastModified": "2026-08-24T20:34:54+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970027", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845995+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414187+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7b90b214f26488aa737d01d1b4bb16c", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970032", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845997+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414229+00:00", "framework": "vllm-patch-tokenizer", "intentId": "79ac4416532e431ca1d10b0239a851bc", "lastModified": "2026-09-15T14:59:20+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970030", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.845999+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414270+00:00", "framework": "vllm-patch-tokenizer", "intentId": "664522c0569742d7a0dc1e92d812f5c6", "lastModified": "2026-09-14T19:46:18+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970033", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846002+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414311+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ae690d6e12d0410b831ca54bc0ef7038", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "reason": null, "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970031", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846005+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414353+00:00", "framework": "vllm-patch-tokenizer", "intentId": "83a2d29587ac4481892a99108bb3e3dd", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "reason": null, "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970034", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846007+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414394+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9228f38bcfda48a1a267b095d71e761c", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846010+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414436+00:00", "framework": "vllm-patch-tokenizer", "intentId": "303974583fbe48a09e4bd24cefaf62dc", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "reason": null, "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846013+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414477+00:00", "framework": "vllm", "intentId": "fa63e7ca09c141febba0d1ae93c17a51", "lastModified": "2026-08-24T20:33:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970037", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846016+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414525+00:00", "framework": "vllm", "intentId": "7d4a0e14bf46430499b4e31b6a8be72d", "lastModified": "2026-08-24T20:28:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970044", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846018+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414573+00:00", "framework": "vllm", "intentId": "bc0954808f98484e8f5e5bf061aeaf63", "lastModified": "2026-08-24T20:25:20+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970042", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846021+00:00", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414620+00:00", "framework": "vllm", "intentId": "81ec521e02c6416380793c47b1d54e9d", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "reason": null, "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970038", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846023+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414673+00:00", "framework": "vllm-customized", "intentId": "b78f68a2a4ab46fb81deed30b7be615c", "lastModified": "2026-08-26T18:34:54+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "reason": null, "repoId": "ornith-ai/Ornith-1.5-9B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970040", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846026+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414731+00:00", "framework": "vllm-customized", "intentId": "06bf50cc38064f5589f6dd3afc99bdde", "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": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970045", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846029+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414787+00:00", "framework": "vllm", "intentId": "fa32db56d72546efabf9b973efe4fcdb", "lastModified": "2026-08-26T12:23:38+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "reason": null, "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "4970043", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846031+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414843+00:00", "framework": "vllm", "intentId": "4ac2bcb16c4f41d6b96b7e6d08309237", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "reason": null, "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970039", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846033+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414886+00:00", "framework": "vllm", "intentId": "e0ba7290bad645e0a89a5783afec2ad1", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970041", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846036+00:00", "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414928+00:00", "framework": "vllm", "intentId": "5d7ccaa875f84600aed53eddb056921d", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970047", "taskType": "text-generation"}
{"batchId": "6e32ee0e1378494296b42ee3c2527006", "completedAt": "2026-09-20T03:41:49.846038+00:00", "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:41:41.414970+00:00", "framework": "vllm", "intentId": "7f583607a33b45738e0e1d567dd10773", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "reason": null, "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4970046", "taskType": "text-generation"}
{"batchId": "a0638aa6b9d441fc8127d1ff98b0380e", "completedAt": "2026-09-20T02:22:36.529135+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-10T13:27:22.633245+00:00", "framework": "vllm", "intentId": "8986a9476a034876a874432fe981a93c", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "success", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation"}
{"batchId": "3601d2529e2f4dbab4abc91721a031a6", "completedAt": "2026-09-20T01:08:42.115049+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-19T12:27:15.291074+00:00", "framework": "vllm_tokenizer_patch", "intentId": "56909ec2a21e4e3f9e0a55deb70d46c0", "repoId": "Arain119/Sophia", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "failed", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "taskType": "text-generation"}
{"batchId": "17f9bc75c9254b23a97517096a945dfd", "completedAt": "2026-09-20T00:27:18.357432+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-09T17:53:27.791335+00:00", "framework": "vllm-mlu", "intentId": "e8b41bd8a15a4f4ab9051c3e998dfc85", "repoId": "laion/swesmith-nl2bash-stack-bugsseq", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "success", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation"}

43
.modelhub_state/routing_intelligence.json
View File

@@ -1,42 +1,43 @@
{
"acceptedByCategory": {
"unified_success_first": 1431
"unified_success_first": 1495
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 17,
"text-generation|Ascend_910-b3|vllm": 30,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 106,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 107,
"text-generation|Ascend_910-b4|llamacpp": 13,
"text-generation|Ascend_910-b4|vllm": 13,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 93,
"text-generation|Biren_166m|vllm": 63,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 96,
"text-generation|Biren_166m|vllm": 65,
"text-generation|Biren_166m|vllm_fix_tokenizer": 13,
"text-generation|Cambricon_mlu-370-x4|vllm": 38,
"text-generation|Cambricon_mlu-370-x4|vllm": 42,
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 1,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 75,
"text-generation|Cambricon_mlu-370-x8|vllm": 18,
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 11,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 79,
"text-generation|Cambricon_mlu-370-x8|vllm": 23,
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 13,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 80,
"text-generation|Iluvatar_bi-150|llamacpp": 16,
"text-generation|Iluvatar_bi-150|transformers": 1,
"text-generation|Iluvatar_bi-150|vllm": 6,
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 83,
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 5,
"text-generation|Iluvatar_mrv-100|vllm": 57,
"text-generation|Kunlunxin_p-800|vllm": 1,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 149,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 30,
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 86,
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 11,
"text-generation|Iluvatar_mrv-100|vllm": 60,
"text-generation|Kunlunxin_p-800|vllm": 2,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 150,
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 34,
"text-generation|MetaX_c-500|vllm": 101,
"text-generation|Mthreads_s4000|llamacpp": 17,
"text-generation|Mthreads_s4000|vllm": 89,
"text-generation|Mthreads_s4000|vllm": 90,
"text-generation|Sunrise_pt-200-x1|vllm": 62,
"text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 62,
"text-generation|Vastai_va16|vllm_fix_tokenizer": 52,
"text-generation|Vastai_va16|vllm_fix_tokenizer": 61,
"text-generation|hygon_k100-ai|llamacpp": 18,
"text-generation|hygon_k100-ai|vllm": 22,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 91
"text-generation|hygon_k100-ai|vllm": 26,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 104
},
"acceptedSinceRefresh": 1431,
"acceptedTotal": 1431,
"generatedAt": "2026-09-20T03:40:44.569090+00:00",
"acceptedSinceRefresh": 1495,
"acceptedTotal": 1495,
"generatedAt": "2026-09-20T03:41:49.799336+00:00",
"version": 1
}

128
ledger/submissions.jsonl
View File

@@ -782,70 +782,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B", "modelId": "LiquidAI/LFM2.5-2.6B", "submitTime": "2026-09-20T03:40:44.507984+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T16:07:42.654192+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722475", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-09T00:13:45.146237+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "modelId": "nm-testing/nonuniform", "submitTime": "2026-09-08T06:46:06.780642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712802", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.532675+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712815", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.601676+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712820", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-08T06:46:11.589203+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712819", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "submitTime": "2026-09-08T23:02:45.685300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729504", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-08T23:02:51.818347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729510", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.847566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729520", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-08T23:02:51.830682+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729514", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.824770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.913002+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729521", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T23:02:52.084632+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.142420+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.155081+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-05T13:47:55.466466+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649912", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-06T15:28:09.684321+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669863", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T06:46:11.531728+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "submitTime": "2026-09-08T23:02:45.784701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729501", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "submitTime": "2026-09-08T23:02:45.697968+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729508", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/Qwen3.5-35B-A3B-hygon-FlagOS", "modelId": "FlagRelease/Qwen3.5-35B-A3B-hygon-FlagOS", "submitTime": "2026-09-08T23:02:51.829157+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729513", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/Qwen3.5-35B-A3B-iluvatar-FlagOS", "modelId": "FlagRelease/Qwen3.5-35B-A3B-iluvatar-FlagOS", "submitTime": "2026-09-08T23:02:51.822402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729511", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.843439+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729517", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.889698+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729518", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-08T23:02:51.841387+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729516", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.888188+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729519", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-08T23:02:51.995104+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729526", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "submitTime": "2026-09-08T23:02:51.985375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/vastai-ais/GLM-OCR-FP8", "modelId": "vastai-ais/GLM-OCR-FP8", "submitTime": "2026-09-04T21:32:51.205525+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634661", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-05T09:38:43.488297+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645739", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-05T16:20:38.387161+00:00", "targetGpu": "Vastai_va16", "taskId": "4651795", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-05T16:23:35.585208+00:00", "targetGpu": "Vastai_va16", "taskId": "4651830", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-06T00:30:35.485447+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657895", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-4bit", "submitTime": "2026-09-06T00:30:40.389876+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-06T00:30:40.585784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657913", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-06T02:28:43.876366+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659340", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ZHTODD/llm-study-model", "modelId": "ZHTODD/llm-study-model", "submitTime": "2026-09-06T12:37:22.509920+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667092", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-06T15:28:09.686082+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669861", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-bf16", "modelId": "mlx-community/Qwen3.8-27B-MTP-bf16", "submitTime": "2026-09-06T20:59:59.616196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678098", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "submitTime": "2026-09-04T03:57:15.119872+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610784", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-04T03:57:15.184550+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610787", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T03:57:15.188888+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610783", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/qwen36-reap-2k-mlx-q8", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "submitTime": "2026-09-04T20:36:22.385440+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633906", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-04T20:41:27.058068+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633956", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "submitTime": "2026-09-04T20:42:22.700314+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633978", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-04T21:21:28.856839+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634507", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4", "modelId": "groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4", "submitTime": "2026-09-04T22:28:19.770846+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635468", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-04T23:07:33.297152+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635981", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "submitTime": "2026-09-05T09:00:09.135600+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645040", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T16:20:38.390632+00:00", "targetGpu": "Vastai_va16", "taskId": "4651793", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-05T16:30:08.482261+00:00", "targetGpu": "Vastai_va16", "taskId": "4651930", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-06T04:36:19.394975+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661051", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "submitTime": "2026-09-06T04:36:19.350592+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661017", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T06:46:30.091299+00:00", "targetGpu": "MetaX_c-500", "taskId": "4662728", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-06T07:25:42.990583+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663206", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-04T08:10:58.188745+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622622", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"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": "2026-09-04T08:21:52.578870+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622780", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"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": "2026-09-04T09:20:12.202888+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4623811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-04T14:16:10.707417+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4627927", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "submitTime": "2026-09-04T16:10:19.959444+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629855", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-04T21:05:48.185454+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634349", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-04T21:16:21.226380+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634451", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-04T21:32:51.155921+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634658", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
@@ -962,3 +898,67 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-20T03:25:32.546681+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969665", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T03:25:32.539673+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-20T03:25:32.535865+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:42.237083+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969989", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:42.246689+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969991", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-20T03:41:42.243785+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969987", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "submitTime": "2026-09-20T03:41:42.249155+00:00", "targetGpu": "Vastai_va16", "taskId": "4969994", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"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": "2026-09-20T03:41:42.236412+00:00", "targetGpu": "Vastai_va16", "taskId": "4969990", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"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": "2026-09-20T03:41:42.238130+00:00", "targetGpu": "Vastai_va16", "taskId": "4969985", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "submitTime": "2026-09-20T03:41:42.239144+00:00", "targetGpu": "Vastai_va16", "taskId": "4969988", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:41:42.241690+00:00", "targetGpu": "Vastai_va16", "taskId": "4969986", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:41:42.247748+00:00", "targetGpu": "Vastai_va16", "taskId": "4969992", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-20T03:41:42.240363+00:00", "targetGpu": "Vastai_va16", "taskId": "4969984", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T03:41:42.245581+00:00", "targetGpu": "Vastai_va16", "taskId": "4969995", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:41:42.242718+00:00", "targetGpu": "Vastai_va16", "taskId": "4969993", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "submitTime": "2026-09-20T03:41:48.957764+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969998", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-20T03:41:48.962596+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970005", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-20T03:41:49.051083+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970006", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-20T03:41:49.009007+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970003", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-20T03:41:48.960695+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970000", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T03:41:48.976356+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970002", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T03:41:48.969580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969996", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "modelId": "BAAI/RoboBrain2.5-8B-MT", "submitTime": "2026-09-20T03:41:49.003635+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970004", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-kunlunxin-p-800"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "submitTime": "2026-09-20T03:41:48.972177+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969999", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "modelId": "BAAI/RoboBrain2.5-8B-NV", "submitTime": "2026-09-20T03:41:48.995904+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970001", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-20T03:41:48.973538+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969997", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "submitTime": "2026-09-20T03:41:49.061655+00:00", "targetGpu": "Biren_166m", "taskId": "4970007", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "submitTime": "2026-09-20T03:41:49.141735+00:00", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-20T03:41:49.155389+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "modelId": "XHToken/Spark-X2.5-4B", "submitTime": "2026-09-20T03:41:49.135089+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "modelId": "XHToken/Spark-X2.5-1.7B", "submitTime": "2026-09-20T03:41:49.149678+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970015", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-20T03:41:49.140281+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970016", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-20T03:41:49.138985+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970013", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "submitTime": "2026-09-20T03:41:49.147134+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970014", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "submitTime": "2026-09-20T03:41:49.153153+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970011", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "submitTime": "2026-09-20T03:41:49.145647+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970009", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-20T03:41:49.160353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-20T03:41:49.302550+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970020", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T03:41:49.292011+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970019", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-20T03:41:49.299361+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970021", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "submitTime": "2026-09-20T03:41:49.339898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970022", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-20T03:41:49.297736+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970018", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-iluvatar-bi-150"}
{"framework": "transformers", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "submitTime": "2026-09-20T03:41:49.365180+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970023", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "submitTime": "2026-09-20T03:41:49.389155+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970024", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "modelId": "LiquidAI/LFM2.5-8B-A1B", "submitTime": "2026-09-20T03:41:49.436619+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970026", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-20T03:41:49.434722+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-20T03:41:49.404067+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970025", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-20T03:41:49.406151+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:49.439481+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970027", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-20T03:41:49.466295+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970032", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "submitTime": "2026-09-20T03:41:49.456169+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970030", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-20T03:41:49.472121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970033", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-20T03:41:49.460113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970031", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "modelId": "pfnet/plamo-3-nict-8b-base", "submitTime": "2026-09-20T03:41:49.536503+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970034", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "submitTime": "2026-09-20T03:41:49.545556+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "modelId": "inceptionai/Jais-2-8B-Chat", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:49.639515+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970037", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:49.650158+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970044", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-20T03:41:49.645606+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970042", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-20T03:41:49.638140+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970038", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x4"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-20T03:41:49.636924+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970040", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-20T03:41:49.651764+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970045", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"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": "2026-09-20T03:41:49.643588+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970043", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-20T03:41:49.636332+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970039", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-20T03:41:49.641475+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970041", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "submitTime": "2026-09-20T03:41:49.745068+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "submitTime": "2026-09-20T03:41:49.739370+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970046", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}

14
manifest.json
View File

@@ -9,16 +9,16 @@
".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe",
".modelhub_state/recent_outcomes.jsonl": "8b230beac27183f4f5f556eaa061dbc77bdcc47b761f379a572673e0fba55aaa",
".modelhub_state/recovery_active_tasks.jsonl": "3f155b8997ff2e246933dd9824ffe08bb728695651f2f8e7d9b783b7604ea7c2",
".modelhub_state/recovery_intents.jsonl": "4834a5d0033b70253f9c04f153b6a1ad0f31c007645b25a6250307ed15dfbb27",
".modelhub_state/routing_intelligence.json": "cc43ea2cbdc7a6ad1d232c348432bac65708780e6dc7a200046894dbe893bbc1",
".modelhub_state/recovery_intents.jsonl": "7a303297524d641ef74531e0cd5d504f002dc937ea260066d9bd5c142d10fe28",
".modelhub_state/routing_intelligence.json": "fbf09541f0e3106ddd00e17b7f447a1e4408a99934c981532b35aaf9ce345f20",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "04e35ff5a61b63ad4e47debbc005a5f64fafc1e49087c580116ec7c2b496003c",
"outcomes/submissions.jsonl": "d5af1b1211c54c3e20bd2240bc8d3f8810838c779943feb5a37bb5ad2b17e22b"
"ledger/submissions.jsonl": "75076095fda5b1f06b25f10b776cfef75b59f7e25f983cbfede3ef5027a9a7ea",
"outcomes/submissions.jsonl": "3d2f0014b574b52868144b1ee4c48889bcdb5383d06b1b2e5ede06f82ac891bd"
},
"generation": 10141,
"phase": "intent",
"generation": 10142,
"phase": "result",
"schemaVersion": 1,
"updatedAt": "2026-09-20T03:41:41.563047+00:00",
"updatedAt": "2026-09-20T03:41:49.937040+00:00",
"writerId": "f67e4ec113c04968a9d9484fb8e36bd4"
}

64
outcomes/submissions.jsonl
View File

@@ -817,3 +817,67 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "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": 507443052}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:40:44.507984+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969968", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.237083+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969989", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.246689+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969991", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.243785+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969987", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": 1248516007, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.249155+00:00", "targetGpu": "Vastai_va16", "taskId": "4969994", "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": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:41:42.236412+00:00", "targetGpu": "Vastai_va16", "taskId": "4969990", "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": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:41:42.238130+00:00", "targetGpu": "Vastai_va16", "taskId": "4969985", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809686744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.239144+00:00", "targetGpu": "Vastai_va16", "taskId": "4969988", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "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:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.241690+00:00", "targetGpu": "Vastai_va16", "taskId": "4969986", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "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": 23556606333}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.247748+00:00", "targetGpu": "Vastai_va16", "taskId": "4969992", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.240363+00:00", "targetGpu": "Vastai_va16", "taskId": "4969984", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:42.245581+00:00", "targetGpu": "Vastai_va16", "taskId": "4969995", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": "2026-09-20T03:41:42.242718+00:00", "targetGpu": "Vastai_va16", "taskId": "4969993", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.957764+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969998", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.962596+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970005", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.051083+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970006", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.009007+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970003", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.960695+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.976356+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.969580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969996", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.003635+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970004", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.972177+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969999", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.995904+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970001", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.973538+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969997", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.061655+00:00", "targetGpu": "Biren_166m", "taskId": "4970007", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.141735+00:00", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.155389+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.135089+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.149678+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970015", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.140281+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970016", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.138985+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970013", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.147134+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970014", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.153153+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970011", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.145647+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970009", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.160353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.302550+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.292011+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970019", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.299361+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.339898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970022", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.297736+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970018", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.365180+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970023", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.389155+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970024", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.436619+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970026", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "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:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.434722+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.404067+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970025", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.406151+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "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": 507443052}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.439481+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970027", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 955857175, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.466295+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970032", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "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": 9036402901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.456169+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "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:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.472121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970033", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "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:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.460113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970031", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.536503+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970034", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:41:49.545556+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.639515+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970037", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.650158+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970044", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.645606+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970042", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.638140+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970038", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:41:49.636924+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970040", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:41:49.651764+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970045", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663548868}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.643588+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.636332+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970039", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.641475+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970041", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.745068+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "e4f10af7e21b1a730b2dfa32856745ab0e7a14867778026d61065fda3de90727", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.739370+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970046", "taskType": "text-generation", "verifyResult": null}