diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 90b53375d..3eba34916 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -922,7 +922,7 @@ {"batchId": "a2125561c37f45f5acf6207a9eda4e0a", "completedAt": "2026-09-18T17:56:52.419964+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-18T17:56:46.638693+00:00", "framework": "vllm-mlu", "intentId": "e26cf829fb0547e3a570fcbeb99dcee8", "lastModified": "2026-09-16T16:32:52+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-7B-FP8", "reason": null, "reconciledAt": "2026-09-18T18:36:15.111836+00:00", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938209", "taskType": "text-generation"} {"batchId": "4cb042c4dbd54b9da0b49f912af887f1", "completedAt": "2026-09-18T18:17:30.001387+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-18T18:17:21.337371+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bc1948fec59f416aa516b65ed74cd3ce", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "reconciledAt": "2026-09-18T18:36:15.145969+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4938406", "taskType": "text-generation"} {"batchId": "6629ad0dccc24c57ae8050f953bb6093", "completedAt": "2026-09-18T18:34:36.655741+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-18T18:34:31.131543+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5968e9365a124249a8fae510d01b8f77", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "reconciledAt": "2026-09-18T18:36:15.145823+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4938618", "taskType": "text-generation"} -{"batchId": "e63aad111bc74f4585459ae69a98be4a", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-18T18:41:54.981327+00:00", "framework": "vllm-mlu", "intentId": "f0794e575c6745abbd39c57cc214b924", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e63aad111bc74f4585459ae69a98be4a", "completedAt": "2026-09-18T18:42:00.905384+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-18T18:41:54.981327+00:00", "framework": "vllm-mlu", "intentId": "f0794e575c6745abbd39c57cc214b924", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation"} {"batchId": "8d27d6d5a99748efbdd97223e640c598", "completedAt": "2026-09-18T14:35:12.136557+00:00", "configFingerprint": "359725c5cf0821e26681bc436dad944747db4ac72a1bf9e70b5f6f8e63a023b4", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:35:06.015304+00:00", "framework": "llamacpp", "intentId": "10303336f4f24e2f98aa86764cc2f0fc", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "bfd8069a25c5437f87c1eb1f45b313b1", "completedAt": "2026-09-18T14:33:31.434713+00:00", "configFingerprint": "e1276bf11e548198418262ddca64a6c4514301bb26e65ecc7e04f8d8f0442b6b", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:33:23.815503+00:00", "framework": "llamacpp", "intentId": "3c35cff71fae4e2997f1d1fa492cdda8", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "18470fd259dd4f84ad6911206103ac42", "completedAt": "2026-09-18T14:31:05.798368+00:00", "configFingerprint": "680fcdbc0952bbae15ed7a5a114782d3eaa8806d60778df64b3e1a99d41a066b", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:30:53.123908+00:00", "framework": "llamacpp", "intentId": "c7daff34b5a4470ab91e00ee1da68653", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 9d38138d0..300414ba7 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1057 + "unified_success_first": 1058 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 16, @@ -10,7 +10,7 @@ "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 48, "text-generation|Biren_166m|vllm": 56, "text-generation|Biren_166m|vllm_fix_tokenizer": 13, - "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 46, + "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 47, "text-generation|Cambricon_mlu-370-x8|vllm": 13, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 9, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 76, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 16, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 62 }, - "acceptedSinceRefresh": 1057, - "acceptedTotal": 1057, - "generatedAt": "2026-09-18T18:34:36.624179+00:00", + "acceptedSinceRefresh": 1058, + "acceptedTotal": 1058, + "generatedAt": "2026-09-18T18:42:00.874427+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index e75613c7f..8672b654a 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -734,3 +734,4 @@ {"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/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} diff --git a/manifest.json b/manifest.json index 24cff4f68..b1c220519 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "3c142558258883a3e45602d09e9392c46bfde3deae83aabc51d01f3b1c2d91d9", ".modelhub_state/recent_outcomes.jsonl": "dd405ee2b1dedd7cc25d9e2aea5b5dde33665f0a08e07699040bcd9108ad5aa2", ".modelhub_state/recovery_active_tasks.jsonl": "21c2bc5baea290c6631b3e6e8179d8e517f9f5b0bb26a2f3c95db5bc395f5f78", - ".modelhub_state/recovery_intents.jsonl": "58626d5fb013a7f9a921c8f9118448f0c5a1230ddd32ad4e46fd5b0e56044177", - ".modelhub_state/routing_intelligence.json": "2adc778694656c14c8ca36fa9540ad69c0aa9064042d20f07f2055de110ff6be", + ".modelhub_state/recovery_intents.jsonl": "cf96260363c21243f2eb9ae555d691f328da068d602ae0b88be9298a0730998d", + ".modelhub_state/routing_intelligence.json": "0cbe9b78d9ee805842cfbebbebaea608f5aaa4e109286e399ba5d0b81e4dfe02", ".modelhub_state/submission_exclusions.jsonl": "cd362b9c480f30eb8106e264359b19b37b894120db54586e63b0a0d1d41a73b0", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "ea9c8fce98763e78f76cc3f1e72b4d0ab60b18216288592750e63c2cf5133479", - "outcomes/submissions.jsonl": "b9a2c803d664514c9f3f8ece58d8b1637f8e016281ad49477d30fb0565148b4a" + "ledger/submissions.jsonl": "2c334e7d071c41915210bffc505a2885ec0d966282d60449e9726bb28c9d16ae", + "outcomes/submissions.jsonl": "ac91c2d1d4af723b4eb4e0690d00de80f30fa6fafa9f061a49227c9403cd5554" }, - "generation": 9409, - "phase": "intent", + "generation": 9410, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-18T18:41:55.059656+00:00", + "updatedAt": "2026-09-18T18:42:01.015794+00:00", "writerId": "217f1806b49c401894bed7ce18be9095" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 79fe86bab..280994a5e 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -541,3 +541,4 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T17:56:47.449292+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938209", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T18:17:22.750439+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4938406", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T18:34:31.787488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4938618", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}