From 2f713387f4939fc5a43705beb98e2276c8bb8d42 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Fri, 18 Sep 2026 19:38:41 +0000 Subject: [PATCH] state: generation 9436 (result) --- .modelhub_state/recovery_intents.jsonl | 2 +- .modelhub_state/routing_intelligence.json | 10 +++++----- ledger/submissions.jsonl | 1 + manifest.json | 14 +++++++------- outcomes/submissions.jsonl | 1 + 5 files changed, 15 insertions(+), 13 deletions(-) diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index c7dae9b41..e45e1a4e1 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -925,7 +925,7 @@ {"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, "reconciledAt": "2026-09-18T19:35:22.513160+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation"} {"batchId": "1678c8f01d1345699becdedd5e17a9ee", "completedAt": "2026-09-18T18:58:35.153151+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-18T18:58:27.799841+00:00", "framework": "vllm", "intentId": "dea853da75cc4b059932f50bbac3fc9d", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "reconciledAt": "2026-09-18T19:35:22.513477+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation"} {"batchId": "3f754877a40f453798df858d73b6c517", "completedAt": "2026-09-18T19:15:36.647953+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-18T19:15:30.192168+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e1cc077415f04f00838b99c98e26c2df", "lastModified": "2026-08-25T14:08:37+00:00", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "reason": null, "reconciledAt": "2026-09-18T19:35:22.513700+00:00", "repoId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4939007", "taskType": "text-generation"} -{"batchId": "50c842d3c42048f29d4cb13db73fe5e1", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-18T19:38:30.648880+00:00", "framework": "vllm-customized", "intentId": "3a2ec84c5351458c83947fbde464d42d", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "50c842d3c42048f29d4cb13db73fe5e1", "completedAt": "2026-09-18T19:38:41.393285+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-18T19:38:30.648880+00:00", "framework": "vllm-customized", "intentId": "3a2ec84c5351458c83947fbde464d42d", "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, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "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 7112f2493..cc73b6066 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 1060 + "unified_success_first": 1061 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 16, @@ -12,7 +12,7 @@ "text-generation|Biren_166m|vllm_fix_tokenizer": 13, "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-customized": 10, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 76, "text-generation|Iluvatar_bi-150|llamacpp": 13, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 77, @@ -27,8 +27,8 @@ "text-generation|hygon_k100-ai|llamacpp": 16, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 63 }, - "acceptedSinceRefresh": 1060, - "acceptedTotal": 1060, - "generatedAt": "2026-09-18T19:15:36.617651+00:00", + "acceptedSinceRefresh": 1061, + "acceptedTotal": 1061, + "generatedAt": "2026-09-18T19:38:41.363457+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 703a27088..aaa3c50ed 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -736,3 +736,4 @@ {"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-customized", "modelAddress": "https://modelscope.cn/models/barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "submitTime": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 81224d447..76d50f8eb 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": "223e81a4e2513eeef78fd060e79e721c9a0e9cd814191013b46806f3ef89a665", - ".modelhub_state/recovery_intents.jsonl": "fa83231be900b210f1a544ae92a8405161842238220c037af4a3c5f607357cf2", - ".modelhub_state/routing_intelligence.json": "f190ed492d725a6b3f41efa98ee7da9ec4f4b881a5e3dd18833e703b0ffd7f8b", + ".modelhub_state/recovery_intents.jsonl": "0aad2f905fc62fe15418617fdf5cf8fe2accbeef011e5f9f684fa1e73ff07c60", + ".modelhub_state/routing_intelligence.json": "794363d7f5faa10fc560903b4aa7aaff37082c6f5b980a0b273131fcdb7dad9d", ".modelhub_state/submission_exclusions.jsonl": "cd362b9c480f30eb8106e264359b19b37b894120db54586e63b0a0d1d41a73b0", ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23", - "ledger/submissions.jsonl": "77a0064a711eb68871b732e13f0579d68911827c48842b26f38a405c04c3f4fd", - "outcomes/submissions.jsonl": "931e048f211a9b5f99d1f498f65318650e9d68d5b74bbd98274ce18af3831211" + "ledger/submissions.jsonl": "6eaff4edbc2da59503e2fc0431088873cbe6a4c07d05e0745452bcc7e900559a", + "outcomes/submissions.jsonl": "5d2878db43473f203a12ac7e960dd3520fc3dcffe7299cf550c3af03938d5ce3" }, - "generation": 9435, - "phase": "intent", + "generation": 9436, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-18T19:38:30.727407+00:00", + "updatedAt": "2026-09-18T19:38:41.461337+00:00", "writerId": "217f1806b49c401894bed7ce18be9095" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 551b5c6df..e1f8fb7c4 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -537,3 +537,4 @@ {"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} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-18T19:15:30.844293+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4939007", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "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": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "verifyResult": null}