diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 2bcb1ec17a..f4c71fffbf 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -1439,20 +1439,20 @@ {"batchId": "253a01e2e0f348f88e7bf885b4ce7998", "completedAt": "2026-09-20T03:58:41.487678+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:58:34.702045+00:00", "framework": "vllm-customized", "intentId": "84b705e1b1b149bbb36b86075e4059b4", "lastModified": "2026-09-17T12:51:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "reason": null, "reconciledAt": "2026-09-20T04:01:50.176020+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation"} {"batchId": "253a01e2e0f348f88e7bf885b4ce7998", "completedAt": "2026-09-20T03:58:41.487681+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T03:58:34.702104+00:00", "framework": "vllm", "intentId": "f36c097da1634835be2de0ac131b8899", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "reason": null, "reconciledAt": "2026-09-20T04:01:50.175616+00:00", "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation"} {"batchId": "13a57ff3db9a4b54864ca55fbf762fca", "completedAt": "2026-09-20T04:01:48.942943+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:01:41.833924+00:00", "framework": "vllm", "intentId": "8403f8916cad44778c382ae5704f8d51", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T04:01:50.177343+00:00", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4970409", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509065+00:00", "framework": "vllm_tokenizer_patch", "intentId": "115abd9a47c344aa9108b676686444c5", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509170+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f34624d11bd74be885e7994d02097349", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509224+00:00", "framework": "vllm_tokenizer_patch", "intentId": "772f6b03205d437a8ab0abb0daafe8a7", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509274+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "171c0d7d34354704a302e81be18af3d6", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509321+00:00", "framework": "vllm", "intentId": "460922fddb5d4509afb9f6ad423a541b", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509379+00:00", "framework": "vllm", "intentId": "441ae0a8f1f7494cb28ae9fbbd1d48a9", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509436+00:00", "framework": "vllm", "intentId": "1864f9ce54dd4b39a971278fa68d3dc5", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509492+00:00", "framework": "vllm", "intentId": "09a18866d47d462893b41e8b261ab505", "lastModified": "2026-09-19T14:48:58+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509547+00:00", "framework": "vllm", "intentId": "168198af586f41849740cff640e836e8", "lastModified": "2026-09-19T14:28:18+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509602+00:00", "framework": "vllm", "intentId": "e60f1c3f48e242a0b38966bc4977474b", "lastModified": "2026-09-19T14:42:49+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509656+00:00", "framework": "vllm", "intentId": "eedc229a84dd463e80253fcd611ec53a", "lastModified": "2026-09-19T14:43:57+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509728+00:00", "framework": "vllm", "intentId": "ac3407f94e4642a7937a6c5d25795ffa", "lastModified": "2026-09-19T14:37:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509782+00:00", "framework": "vllm", "intentId": "8184ac02a993475fb468a3cf94510498", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} -{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509836+00:00", "framework": "vllm", "intentId": "041f741814db4d97b51351087094a587", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320000+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509065+00:00", "framework": "vllm_tokenizer_patch", "intentId": "115abd9a47c344aa9108b676686444c5", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970439", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320012+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509170+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f34624d11bd74be885e7994d02097349", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "reason": null, "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970436", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320017+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509224+00:00", "framework": "vllm_tokenizer_patch", "intentId": "772f6b03205d437a8ab0abb0daafe8a7", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4970444", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320020+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509274+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "171c0d7d34354704a302e81be18af3d6", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "reason": null, "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320024+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509321+00:00", "framework": "vllm", "intentId": "460922fddb5d4509afb9f6ad423a541b", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "reason": null, "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "submitted", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320028+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509379+00:00", "framework": "vllm", "intentId": "441ae0a8f1f7494cb28ae9fbbd1d48a9", "lastModified": "2026-09-12T12:30:14+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "reason": null, "repoId": "OpenBMB/MiniCPM5-2B-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320031+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509436+00:00", "framework": "vllm", "intentId": "1864f9ce54dd4b39a971278fa68d3dc5", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "reason": null, "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320034+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509492+00:00", "framework": "vllm", "intentId": "09a18866d47d462893b41e8b261ab505", "lastModified": "2026-09-19T14:48:58+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970443", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320038+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509547+00:00", "framework": "vllm", "intentId": "168198af586f41849740cff640e836e8", "lastModified": "2026-09-19T14:28:18+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970442", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320041+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509602+00:00", "framework": "vllm", "intentId": "e60f1c3f48e242a0b38966bc4977474b", "lastModified": "2026-09-19T14:42:49+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "reason": null, "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320044+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509656+00:00", "framework": "vllm", "intentId": "eedc229a84dd463e80253fcd611ec53a", "lastModified": "2026-09-19T14:43:57+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320047+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509728+00:00", "framework": "vllm", "intentId": "ac3407f94e4642a7937a6c5d25795ffa", "lastModified": "2026-09-19T14:37:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "reason": null, "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320051+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509782+00:00", "framework": "vllm", "intentId": "8184ac02a993475fb468a3cf94510498", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "reason": null, "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation"} +{"batchId": "0f19562a039f44e8b6caf3461a50d6f3", "completedAt": "2026-09-20T04:02:52.320054+00:00", "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configSource": "modelhub_live", "createdAt": "2026-09-20T04:02:44.509836+00:00", "framework": "vllm", "intentId": "041f741814db4d97b51351087094a587", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "reason": null, "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 0c4d2681a6..238cd3f85f 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1579 + "unified_success_first": 1593 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -8,19 +8,19 @@ "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 114, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 16, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 98, - "text-generation|Biren_166m|vllm": 66, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 101, + "text-generation|Biren_166m|vllm": 67, "text-generation|Biren_166m|vllm_fix_tokenizer": 13, "text-generation|Cambricon_mlu-370-x4|vllm": 44, "text-generation|Cambricon_mlu-370-x4|vllm-customized": 2, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 77, - "text-generation|Cambricon_mlu-370-x8|vllm": 29, + "text-generation|Cambricon_mlu-370-x8|vllm": 38, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 17, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 81, "text-generation|Iluvatar_bi-150|llamacpp": 16, "text-generation|Iluvatar_bi-150|transformers": 3, "text-generation|Iluvatar_bi-150|vllm": 6, - "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 91, + "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 92, "text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 21, "text-generation|Iluvatar_mrv-100|vllm": 60, "text-generation|Kunlunxin_p-800|vllm": 2, @@ -36,8 +36,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 105 }, - "acceptedSinceRefresh": 1579, - "acceptedTotal": 1579, - "generatedAt": "2026-09-20T04:01:48.887198+00:00", + "acceptedSinceRefresh": 1593, + "acceptedTotal": 1593, + "generatedAt": "2026-09-20T04:02:52.261174+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 8092054b7a..9680b4f71c 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -917,20 +917,6 @@ {"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-20T03:58:41.304973+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-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": "2026-09-20T03:58:41.296912+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-20T04:01:42.646836+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970409", "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-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-08T06:46:11.787458+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712825", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-08T06:46:11.788912+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712827", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-08T06:46:11.785071+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712826", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-08T06:46:11.797429+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712830", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-08T06:46:11.803703+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712829", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-08T06:46:11.884676+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712833", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "submitTime": "2026-09-08T06:46:11.886266+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712834", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-08T06:46:11.927161+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} -{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T15:58:20.200513+00:00", "targetGpu": "Vastai_va16", "taskId": "4722293", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} -{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "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/XYZ-Aquila-mini-OptiQ-4bit", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.440325+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866579", "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/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.438125+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-19T12:09:02.671570+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4956162", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} @@ -960,3 +946,17 @@ {"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_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-20T03:46:29.635942+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970115", "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/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-20T03:46:35.783924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970117", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "submitTime": "2026-09-20T04:02:45.317909+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970439", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "submitTime": "2026-09-20T04:02:45.348395+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970436", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "submitTime": "2026-09-20T04:02:45.354619+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970444", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} +{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "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/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-20T04:02:45.341085+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-20T04:02:45.352471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970443", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-20T04:02:45.350050+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970442", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-20T04:02:45.338954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "submitTime": "2026-09-20T04:02:52.200512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 1decd3fa65..fb81c504bc 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "21a630cefff5c090992ca8360dafe8435b598ca2102f1b9990df6496329a9afe", ".modelhub_state/recent_outcomes.jsonl": "8b230beac27183f4f5f556eaa061dbc77bdcc47b761f379a572673e0fba55aaa", ".modelhub_state/recovery_active_tasks.jsonl": "1219d304014a9f70d16b1c4c53f01d93eee91f7a3b313800da7f6b47191a6549", - ".modelhub_state/recovery_intents.jsonl": "07fc64a0a6f424d66ab0090a78ef3e3208f24efca9ffb76f38b945bc116e6e69", - ".modelhub_state/routing_intelligence.json": "1ae83fb97838550ae312cc123328c06654f00632d29df4ec1851dda17cb8e173", + ".modelhub_state/recovery_intents.jsonl": "8aeafcc7290a5e26f41ea6d8638a5fea8b40fbfd6a882099651dea1df8bf52fd", + ".modelhub_state/routing_intelligence.json": "8b58cf921cfec12f783190aecec957b934468d5b7ff42c2771f36086688303f8", ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "948854d3e238e4f0b98039cc87a84593dafa405b6d3b220cc4d16959a6b18b7b", - "outcomes/submissions.jsonl": "3120da318ccb29b0af7a56fa03354ae58ded6e788c25bc701a56eed4ea9d50ea" + "ledger/submissions.jsonl": "36668ea8be86ef0b7c28ee52dd617d191517748f25e9827fd759c91c02c4a453", + "outcomes/submissions.jsonl": "d08a26c399f1f6365ab9ffe16dc427137185c7abb8914be9bbad97b672508398" }, - "generation": 10166, - "phase": "intent", + "generation": 10167, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-20T04:02:44.674523+00:00", + "updatedAt": "2026-09-20T04:02:52.422940+00:00", "writerId": "f67e4ec113c04968a9d9484fb8e36bd4" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index ad2c26fd4e..753c4d5bcb 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -965,3 +965,17 @@ {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 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": "2026-09-20T03:58:41.304973+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:58:41.296912+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367987, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367987}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:01:42.646836+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970409", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/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": 9093251901, "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": 9093251901}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.317909+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970439", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.348395+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970436", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.354619+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970444", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "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": 7950463197}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.341085+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.352471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970443", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.350050+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970442", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.338954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "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", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "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", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T04:02:52.200512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "taskType": "text-generation", "verifyResult": null}