diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 2c9cb81ea..ea4870341 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -835,7 +835,7 @@ {"batchId": "bc651700058943809a6bab1538da0805", "completedAt": "2026-09-16T15:22:13.901268+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-16T15:22:02.018009+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ed79bde6927146259b091178b6b540e6", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "reason": null, "reconciledAt": "2026-09-16T16:10:08.160424+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4896316", "taskType": "text-generation"} {"batchId": "523249ff3b1e4c408f2334d0a03f1e04", "completedAt": "2026-09-16T15:39:18.948245+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-16T15:39:10.593500+00:00", "framework": "vllm", "intentId": "14fb50346410459f83cab642d531406a", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "reason": null, "reconciledAt": "2026-09-16T16:10:08.159310+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4896984", "taskType": "text-generation"} {"batchId": "6e26193998d74023be1106088d8843d7", "completedAt": "2026-09-16T15:56:32.776391+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-16T15:56:23.565823+00:00", "framework": "vllm", "intentId": "274133e210a64f458dedbd9b5441d961", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "reason": null, "reconciledAt": "2026-09-16T16:10:08.159763+00:00", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4897428", "taskType": "text-generation"} -{"batchId": "06775e5ae24f43ec8d0f323c9c01a695", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-16T16:13:28.561097+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e6e0576b62614583a28b9d38106f8751", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "06775e5ae24f43ec8d0f323c9c01a695", "completedAt": "2026-09-16T16:13:40.521604+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-16T16:13:28.561097+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e6e0576b62614583a28b9d38106f8751", "lastModified": "2026-09-16T16:05:58+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-NV", "reason": null, "repoId": "BAAI/RoboBrain2.5-8B-NV", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "4897844", "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 dcd667453..dc0225860 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,13 +1,13 @@ { "acceptedByCategory": { - "unified_success_first": 970 + "unified_success_first": 971 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 13, "text-generation|Ascend_910-b3|vllm": 16, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 39, "text-generation|Ascend_910-b4|llamacpp": 9, - "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 42, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 43, "text-generation|Biren_166m|vllm": 56, "text-generation|Biren_166m|vllm_fix_tokenizer": 6, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 39, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 13, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 57 }, - "acceptedSinceRefresh": 970, - "acceptedTotal": 970, - "generatedAt": "2026-09-16T15:56:32.738645+00:00", + "acceptedSinceRefresh": 971, + "acceptedTotal": 971, + "generatedAt": "2026-09-16T16:13:40.487109+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index ba4ae9ecb..1bc595d6e 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -801,3 +801,4 @@ {"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/BAAI/RoboBrain2.5-8B-NV", "modelId": "BAAI/RoboBrain2.5-8B-NV", "submitTime": "2026-09-16T16:13:31.480300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4897844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index f0299b546..f0ef4c72a 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466", ".modelhub_state/recent_outcomes.jsonl": "c62a5bc6c77924d26b6d570266710b5821207f6232b6da4c617a15c450ac244c", ".modelhub_state/recovery_active_tasks.jsonl": "9500aa7f1b74b3d0fbbd7695a09b18b36e4c21ce62fc482815bfbf2dac9f6c62", - ".modelhub_state/recovery_intents.jsonl": "c48016c9d44acdee7b979ccf7bd2f9da05496d926cbaef255d4413a66fb2d6f7", - ".modelhub_state/routing_intelligence.json": "0f9c1a6db5a3f0702858929f0f6e71cb30d8bba861a40d0e2d18dd7d547ec4b4", + ".modelhub_state/recovery_intents.jsonl": "3a57760707878412ec56a12e1cf96b6de1d0834e7787d977d5c06c46ca0b009a", + ".modelhub_state/routing_intelligence.json": "fb3210194bd79e8a857c688ec48d5bc3de73dc07f42f702558535aa9a93a8bb0", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", - "ledger/submissions.jsonl": "371dd143df99de47a64390c7a7ff8c6998f2fc2e9b68a33856c145691b1527a5", - "outcomes/submissions.jsonl": "c384d9aa6e4a9ee92e5b0c4f71592f67f1fa518ecb5f557f7dc4a4723bae1ff6" + "ledger/submissions.jsonl": "dc52d955fb7167a05a7193da0bad86435c90bb5139842bd43f1bd6443cab4a4b", + "outcomes/submissions.jsonl": "329c0909a00c46244d3aa79e216ce9981f59bb5111779593a4603a52f2a897c0" }, - "generation": 8274, - "phase": "intent", + "generation": 8275, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-16T16:13:28.694481+00:00", + "updatedAt": "2026-09-16T16:13:40.601125+00:00", "writerId": "eccb3e0018f640d19e578c271a207b5c" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 9402a4f7b..71497dd1e 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -638,3 +638,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T15:22:03.043920+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4896316", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T15:39:11.283539+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4896984", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T15:56:24.313012+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4897428", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545917879, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-16T16:13:31.480300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4897844", "taskType": "text-generation", "verifyResult": null}