diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 9d747a973..882e1ed53 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -859,7 +859,7 @@ {"batchId": "695b34068dbe4d95b7f9caaa76899832", "completedAt": "2026-09-17T10:17:43.417267+00:00", "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:17:25.671043+00:00", "framework": "llamacpp", "intentId": "68be738624f14eeaabd336bfd47c4afe", "lastModified": "2026-09-15T17:45:24+00:00", "modelAddress": "https://modelscope.cn/models/RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "reason": null, "reconciledAt": "2026-09-17T11:37:32.145168+00:00", "repoId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation"} {"batchId": "daeb14c26abd4648a4bb985321b158c8", "completedAt": "2026-09-17T11:10:25.999930+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-17T11:10:15.723589+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4100d6a521b4d6d9680f77771199959", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T11:37:32.146023+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4913855", "taskType": "text-generation"} {"batchId": "3aed3a83a2c44d80b4f4dcd609349a5a", "completedAt": "2026-09-17T11:29:59.295458+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-17T11:29:51.205749+00:00", "framework": "vllm", "intentId": "70eeb0029c374496bc2bbc4a75d064eb", "lastModified": "2026-09-17T10:58:53+00:00", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "reason": null, "reconciledAt": "2026-09-17T11:37:32.144983+00:00", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4914037", "taskType": "text-generation"} -{"batchId": "8945850c54474ace88a46646a7b4b159", "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", "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"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, "repoId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4914180", "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 31ba5e9f1..e23e99ed6 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 994 + "unified_success_first": 995 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 14, @@ -25,10 +25,10 @@ "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 57, "text-generation|Vastai_va16|vllm_fix_tokenizer": 40, "text-generation|hygon_k100-ai|llamacpp": 14, - "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 58 + "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 59 }, - "acceptedSinceRefresh": 994, - "acceptedTotal": 994, - "generatedAt": "2026-09-17T11:29:59.256726+00:00", + "acceptedSinceRefresh": 995, + "acceptedTotal": 995, + "generatedAt": "2026-09-17T11:46:33.716710+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 75118dec8..c41991452 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -770,3 +770,4 @@ {"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-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "submitTime": "2026-09-17T11:46:22.346482+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4914180", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 0fecd225a..58d24ed10 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": "a5b894c19e9ba8c906611e50735dd8e85fe031c2871f3161fccb60bad38161de", - ".modelhub_state/recovery_intents.jsonl": "0bf0f3a7077e8eb89be609b7ed69577759eddb1e018941679f2a9b27446365d5", - ".modelhub_state/routing_intelligence.json": "e44a3b2a19be0646be21b32e24896a303102fc48488173de4fa50e6ee6d9599f", + ".modelhub_state/recovery_intents.jsonl": "ebdc7f61bc4614312b84f30778ba0bb26800fb18d7da99e26a79f179000a6abd", + ".modelhub_state/routing_intelligence.json": "7f7debff76296358f6434126c5969fae45a7a5f0bdeffa6bc30a36822f7e00f4", ".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", - "ledger/submissions.jsonl": "13f7c57bf1d194d0f8fc1eea6bdd312cb2cf09696cb80956e981cb6e521f7f69", - "outcomes/submissions.jsonl": "75cb2e4725cfb11505e5e0c876df34235eb0a0f86a1069fc4b0bcd0d7a225e2c" + "ledger/submissions.jsonl": "29f1b9c73a38baeb1e6986d89927f72c3d104a1e1a7ef9d167d75ba42b65d867", + "outcomes/submissions.jsonl": "ff8f059ce4de502aa87aa6789d99182ee1921404c12fba53cb23aba648123ccc" }, - "generation": 8712, - "phase": "intent", + "generation": 8713, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-17T11:46:21.533917+00:00", + "updatedAt": "2026-09-17T11:46:33.826631+00:00", "writerId": "eccb3e0018f640d19e578c271a207b5c" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index d38208f33..a26e9c2f4 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -592,3 +592,4 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T10:17:26.606251+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 8062180814, "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": "2026-09-17T11:10:16.602977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4913855", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062180814, "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": "2026-09-17T11:29:52.144122+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4914037", "taskType": "text-generation", "verifyResult": null} +{"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}