diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index af40e0c92..b7b0087b6 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -862,7 +862,7 @@ {"batchId": "8945850c54474ace88a46646a7b4b159", "completedAt": "2026-09-17T11:46:33.749715+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-17T11:46:21.395742+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9913cca63f0c4fe3856fa61ac838d07f", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T13:15:36.314174+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4914180", "taskType": "text-generation"} {"batchId": "e833fd41618d461fa526347a420e09ee", "completedAt": "2026-09-17T12:03:55.670914+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-17T12:03:46.742535+00:00", "framework": "vllm", "intentId": "0c6db9d6378c4dc8aea34ad8009a9d17", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T13:15:36.314422+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4914410", "taskType": "text-generation"} {"batchId": "73d7eff730d34f70b320a359489ebef1", "completedAt": "2026-09-17T13:15:34.367643+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-17T13:15:23.944382+00:00", "framework": "vllm", "intentId": "e40ddcb657f54cd4aa63ce0026098a52", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T13:15:36.313292+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "4915199", "taskType": "text-generation"} -{"batchId": "0cb3e2a0d17141959f178d1b29355f42", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-17T13:17:34.268186+00:00", "framework": "vllm-mlu", "intentId": "c31b62ccac2f44689ee9ae593ce73b4c", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "0cb3e2a0d17141959f178d1b29355f42", "completedAt": "2026-09-17T13:17:43.185436+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-17T13:17:34.268186+00:00", "framework": "vllm-mlu", "intentId": "c31b62ccac2f44689ee9ae593ce73b4c", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4915217", "taskType": "text-generation"} {"batchId": "dc557ed173284456b65de02d89689bdd", "completedAt": "2026-09-17T07:00:50.030789+00:00", "configFingerprint": "5ec090e92fba0f8471f90bb0af176a745ebf9604ae8d9957761f2bdcf7b7b894", "configSource": "modelhub_live", "createdAt": "2026-09-17T07:00:42.703320+00:00", "framework": "llamacpp", "intentId": "1e106c48321a4cdea39458e2629ff129", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} {"batchId": "534b216536f14acab0831df3cca7c8b7", "completedAt": "2026-09-17T06:49:28.237705+00:00", "configFingerprint": "4ecf9a1a055b517fbf32a3498eaaf4a2d63b1c33abbcc170dd75fdec6cec9dc6", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:49:18.457343+00:00", "framework": "llamacpp", "intentId": "b99b4231abe54ea698f0d5b126b52b6e", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "88766ff730f64477804cc1605a44aaef", "completedAt": "2026-09-17T06:47:36.731565+00:00", "configFingerprint": "1ab708db1a2ba32a19914fb2b2a3e2674a900769ee64ff9790813f664f2605cb", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:47:30.033650+00:00", "framework": "llamacpp", "intentId": "ab6c54fec18f414bae4f6b66156c2c6a", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index e30d1ad11..628b71286 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 997 + "unified_success_first": 998 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 14, @@ -10,7 +10,7 @@ "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 44, "text-generation|Biren_166m|vllm": 56, "text-generation|Biren_166m|vllm_fix_tokenizer": 6, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 42, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 43, "text-generation|Cambricon_mlu-370-x8|vllm": 13, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 6, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 72, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 14, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 59 }, - "acceptedSinceRefresh": 997, - "acceptedTotal": 997, - "generatedAt": "2026-09-17T13:15:34.335649+00:00", + "acceptedSinceRefresh": 998, + "acceptedTotal": 998, + "generatedAt": "2026-09-17T13:17:43.151649+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 99ae62ab2..5223821e9 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -761,3 +761,4 @@ {"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-mlu", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "submitTime": "2026-09-17T13:17:35.017041+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4915217", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} diff --git a/manifest.json b/manifest.json index a8192690a..4720a8bc0 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8", ".modelhub_state/recent_outcomes.jsonl": "a391daf68a87578021331c170ae71dca18bd55fe9c4e61e89058aa2daac29778", ".modelhub_state/recovery_active_tasks.jsonl": "e85946c2e4ee2c6edf073903844acb30062208744b26e07a477597abd073100c", - ".modelhub_state/recovery_intents.jsonl": "cc209b52c9b11a2458311243136b6800cda3528f9cd9c00e4eff1ab7f3c60176", - ".modelhub_state/routing_intelligence.json": "ca1a8ddbee3a89518c7adc6b3387cd0576338f721b4cb879c79a3d530b497259", + ".modelhub_state/recovery_intents.jsonl": "24ae1395b8549cd22eb1c148a5739a8b33fee23e78d12a26bce462e8956f6edb", + ".modelhub_state/routing_intelligence.json": "e36f9110f9b7415115c0a8f7075f799fbcc5e4a2b2f036efc434af6c509ec979", ".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", - "ledger/submissions.jsonl": "02babdc3112bba3df6959b0450980bf9d2760d583828de939c5871a87c5cb356", - "outcomes/submissions.jsonl": "20a5174757944c5a853a8f68da9f9ca19aeea163a80d18dad2064da067dde265" + "ledger/submissions.jsonl": "1ecdbc4355a10f0625a0ad8912a165f30c15a21a1f591c309542b22cf33c4bfd", + "outcomes/submissions.jsonl": "439566f551bf9b59c578c59064112a540bf28f588cf33392906501586cbb7dea" }, - "generation": 8749, - "phase": "intent", + "generation": 8750, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-17T13:17:34.372391+00:00", + "updatedAt": "2026-09-17T13:17:43.265016+00:00", "writerId": "eccb3e0018f640d19e578c271a207b5c" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 46ab88629..a2cb36f3a 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -592,3 +592,4 @@ {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T11:46:22.346482+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4914180", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T12:03:47.583286+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4914410", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T13:15:25.356637+00:00", "targetGpu": "MetaX_c-500", "taskId": "4915199", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T13:17:35.017041+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4915217", "taskType": "text-generation", "verifyResult": null}