diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 51fe88314..94c059695 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -826,7 +826,7 @@ {"batchId": "3209c84f7df44e298ef28e68f2df8899", "completedAt": "2026-09-16T09:59:59.775218+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-16T09:59:52.031712+00:00", "framework": "vllm", "intentId": "540ed7a21f774994bf68153d41f408af", "lastModified": "2026-09-14T05:44:50+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "reason": null, "reconciledAt": "2026-09-16T13:31:28.236749+00:00", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation"} {"batchId": "7b3a7268f3ee4770b6607791d4f4c1aa", "completedAt": "2026-09-16T10:17:39.909448+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-16T10:17:32.287298+00:00", "framework": "vllm", "intentId": "e216db6de23a402da8a416c5806aae64", "lastModified": "2026-09-14T05:44:50+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "reason": null, "reconciledAt": "2026-09-16T13:31:28.238209+00:00", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation"} {"batchId": "e4af612aa3d5421ea282cf9ca8d3add3", "completedAt": "2026-09-16T12:59:34.973601+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-16T12:59:28.467802+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c778a2b2d8f54d60bb953958c33d37d4", "lastModified": "2026-09-14T05:44:50+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "reason": null, "reconciledAt": "2026-09-16T13:31:28.236746+00:00", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4892870", "taskType": "text-generation"} -{"batchId": "a3a94351c5f046adbe2844572994c080", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-16T13:37:25.981877+00:00", "framework": "vllm_tokenizer_patch", "intentId": "315ae3d2a3534fa78d84dd4ab15679cd", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "a3a94351c5f046adbe2844572994c080", "completedAt": "2026-09-16T13:37:33.823098+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-16T13:37:25.981877+00:00", "framework": "vllm_tokenizer_patch", "intentId": "315ae3d2a3534fa78d84dd4ab15679cd", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "reason": null, "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "4893449", "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 75ee1f13a..2af21e6af 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,11 +1,11 @@ { "acceptedByCategory": { - "unified_success_first": 961 + "unified_success_first": 962 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 13, "text-generation|Ascend_910-b3|vllm": 16, - "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 37, + "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 38, "text-generation|Ascend_910-b4|llamacpp": 9, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 41, "text-generation|Biren_166m|vllm": 56, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 13, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 56 }, - "acceptedSinceRefresh": 961, - "acceptedTotal": 961, - "generatedAt": "2026-09-16T12:59:34.930977+00:00", + "acceptedSinceRefresh": 962, + "acceptedTotal": 962, + "generatedAt": "2026-09-16T13:37:33.781712+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index a54075fd4..3689af519 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -796,3 +796,4 @@ {"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_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "submitTime": "2026-09-16T13:37:27.004498+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4893449", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} diff --git a/manifest.json b/manifest.json index e9ebcc1d5..25d7d2e36 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "dee9467fbfd9b1941e02aab40f46f40feb7e889b1387e997a8c65cdf65c2d707", ".modelhub_state/recent_outcomes.jsonl": "52d3c74c52faf027c74ed17f0bc5f7b42fef66462005416e3195190563b56597", ".modelhub_state/recovery_active_tasks.jsonl": "b4297ab2e064d9d1693a7fa7de46491e6b1da791007983a76e0987bc11bb9ade", - ".modelhub_state/recovery_intents.jsonl": "2a2fb2f55c2af25b622661e709c22049985c4c8c1bc8f7094c710fbedbc40c51", - ".modelhub_state/routing_intelligence.json": "591d2c934a182817a6f6555b49ee817377997da9ad605a138072f7a94f108f96", + ".modelhub_state/recovery_intents.jsonl": "9a9eb7ed55c5077bb34a2a26d4de9269731effb070846904cf15fe54702e0a0e", + ".modelhub_state/routing_intelligence.json": "a15a1e96d6092b9e705a6949f76da6524eff005c54bfa5fbbfd90e336be261fb", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", - "ledger/submissions.jsonl": "6761adfaa615752528bbc8b243aa3106c93ba588076b7b3bd4d961f1aee71dac", - "outcomes/submissions.jsonl": "51255ffb581a60046afa5337baaceeb3c1b7de34902cb093b0cc354c2c10c48b" + "ledger/submissions.jsonl": "ccb8b9c3019492a27c236dd997f52036d9b478f182fcbb4d5e22a7cc7f829796", + "outcomes/submissions.jsonl": "da1566c72d08f6430c61e3e0a52911a981de209188fa335510243bedc1c1174a" }, - "generation": 8205, - "phase": "intent", + "generation": 8206, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-16T13:37:26.171503+00:00", + "updatedAt": "2026-09-16T13:37:33.901674+00:00", "writerId": "eccb3e0018f640d19e578c271a207b5c" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index d72ebc5f2..e3ff31d94 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -636,3 +636,4 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "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": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T09:59:53.000301+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4890315", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "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": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T10:17:32.995862+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4890520", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "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": 4597698253}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T12:59:29.226923+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4892870", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T13:37:27.004498+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4893449", "taskType": "text-generation", "verifyResult": null}