diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 1e1fa3760..1da320da8 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -738,7 +738,7 @@ {"batchId": "8b1a51346103440ea41e5af37f5280d8", "completedAt": "2026-09-14T08:52:31.597026+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-14T08:52:19.962984+00:00", "framework": "vllm", "intentId": "9f1a0f2af05945d39557fc3c712ad59e", "lastModified": "2026-08-29T01:04:55+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "reason": null, "reconciledAt": "2026-09-14T10:39:40.793313+00:00", "repoId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4846441", "taskType": "text-generation"} {"batchId": "b6681cddcbc34739af44fd126a9637a8", "completedAt": "2026-09-14T09:49:24.624973+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-14T09:49:07.682284+00:00", "framework": "vllm-mlu", "intentId": "b025d74c65d94bc681598b852696d05c", "lastModified": "2026-09-14T06:33:18+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-35B-A3B-preview", "reason": null, "reconciledAt": "2026-09-14T10:39:40.794045+00:00", "repoId": "Edge0/Edge0-35B-A3B-preview", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847128", "taskType": "text-generation"} {"batchId": "b6681cddcbc34739af44fd126a9637a8", "completedAt": "2026-09-14T09:49:24.624987+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-14T09:49:07.682391+00:00", "framework": "vllm-mlu", "intentId": "0b48e67d6a094835b86913c4f6aa4935", "lastModified": "2026-08-29T01:04:55+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "reason": null, "reconciledAt": "2026-09-14T10:39:40.792507+00:00", "repoId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847129", "taskType": "text-generation"} -{"batchId": "f95542073d3845e69f43a9c91b1affc7", "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configSource": "modelhub_live", "createdAt": "2026-09-14T10:42:37.433891+00:00", "framework": "llamacpp", "intentId": "e5301f12e1b94dacb908bfdfba42769c", "lastModified": "2026-09-14T10:36:01+00:00", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "repoId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "f95542073d3845e69f43a9c91b1affc7", "completedAt": "2026-09-14T10:42:48.873752+00:00", "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configSource": "modelhub_live", "createdAt": "2026-09-14T10:42:37.433891+00:00", "framework": "llamacpp", "intentId": "e5301f12e1b94dacb908bfdfba42769c", "lastModified": "2026-09-14T10:36:01+00:00", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "reason": null, "repoId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation"} {"batchId": "83639d5151dd4bb78879458f9850c53a", "completedAt": "2026-09-14T06:07:56.622377+00:00", "configFingerprint": "e4588bdbccc377f0f7599581ea0752e64b81eda54f82b575b6aaa81c27ce2e73", "configSource": "modelhub_live", "createdAt": "2026-09-14T06:07:48.751836+00:00", "framework": "llamacpp", "intentId": "35fd7d8028f54640b4d005111704edc0", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "9ea43510e22a43e9991959f19dd0f4a2", "completedAt": "2026-09-13T12:43:37.101071+00:00", "configFingerprint": "7d273c6d9a11c4e826d64fc44d3ae14d805bd3b1e6e663d4dd0b45567cfc5e3f", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:43:27.207464+00:00", "framework": "llamacpp", "intentId": "ab083753c716462fbb8b0529ac182658", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "9370c3290d2242cebbdd1924870f426b", "completedAt": "2026-09-13T12:41:31.618354+00:00", "configFingerprint": "d7cf4e4fcae21f022bbcb9f71b3bb0ab37d6331cf8fd1cd3ad4ba75043690051", "configSource": "modelhub_live", "createdAt": "2026-09-13T12:41:17.857077+00:00", "framework": "llamacpp", "intentId": "8c62b06728694cd9b6f7c5c378f53285", "repoId": "voconly/nemotron-3.5-asr-streaming-0.6b-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 d98bef8bf..5ced92aee 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,9 +1,9 @@ { "acceptedByCategory": { - "unified_success_first": 873 + "unified_success_first": 874 }, "acceptedByRoute": { - "text-generation|Ascend_910-b3|llamacpp": 12, + "text-generation|Ascend_910-b3|llamacpp": 13, "text-generation|Ascend_910-b3|vllm": 16, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 26, "text-generation|Ascend_910-b4|llamacpp": 9, @@ -26,8 +26,8 @@ "text-generation|hygon_k100-ai|llamacpp": 12, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 48 }, - "acceptedSinceRefresh": 873, - "acceptedTotal": 873, - "generatedAt": "2026-09-14T09:49:24.574102+00:00", + "acceptedSinceRefresh": 874, + "acceptedTotal": 874, + "generatedAt": "2026-09-14T10:42:48.830211+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index f457c9f4f..7005a4783 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -789,3 +789,4 @@ {"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": "llamacpp", "modelAddress": "https://modelscope.cn/models/aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"} diff --git a/manifest.json b/manifest.json index 15c2373a4..483dee681 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "e5d9b334b2784235be02767778d1d31aa5d889dbe0cdb9bf65bb77a097c78531", ".modelhub_state/recent_outcomes.jsonl": "7a364026068825178951d4938287669d6d36258e2c985a60370d7c4ba08420cd", ".modelhub_state/recovery_active_tasks.jsonl": "79683500a9fbd9ab501e3457837b2ceb96debd11b830fa44fe594f59e21da700", - ".modelhub_state/recovery_intents.jsonl": "2bfb1bccdcf03d33ab49e9cc809a078595f1ce45cabdab36aedc1b92d7f2afd9", - ".modelhub_state/routing_intelligence.json": "55aee3956ad6545f8272dcc4c4d0e980e7eecbc93d7d5adb9cd8f3e4a2902639", + ".modelhub_state/recovery_intents.jsonl": "c6c339af3b5c48ad23a3280a7ebf3b0d8989f05450948108d2f875562f64b3c4", + ".modelhub_state/routing_intelligence.json": "6c19563c623fc42efe37edde48815ffe21bf6f2ff0258757bc14db37989cb235", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad", - "ledger/submissions.jsonl": "aaa6c42352349208ad59470b84b103f9ed8d4e2b1db57335bbcb8f83f12496ff", - "outcomes/submissions.jsonl": "21ffd4873ada57234270a06e0ad877f1062778ffd3487cd00563089825dd558f" + "ledger/submissions.jsonl": "2f9c74c04544d860af6af802545bfa019e07328f6a2816c6b602b0f7d583b57e", + "outcomes/submissions.jsonl": "4b4fe89a41648354b348b64d3dd14ed6abd3f0057cdfa479cc4acd3ddbfe071b" }, - "generation": 7134, - "phase": "intent", + "generation": 7135, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-14T10:42:37.580213+00:00", + "updatedAt": "2026-09-14T10:42:48.980275+00:00", "writerId": "69701e73196b4ac2b3fad0f412335168" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index fe87107c0..84f6ee1a6 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -635,3 +635,4 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269528840}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T08:52:21.144935+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4846441", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T09:49:08.450169+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847128", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269528840}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T09:49:08.451908+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4847129", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "6270b79db6f53655ba1dc1b7e093937b145df2e6fa5dc1d91f6c309d1008d815", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-14T10:42:38.360078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4847818", "taskType": "text-generation", "verifyResult": null}