From 2ed82c9240a7d18f29cf3e2ce9787c126e0ddebf Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Fri, 11 Sep 2026 16:03:38 +0000 Subject: [PATCH] state: generation 5763 (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 20dbc7fa..453d6f36 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -675,7 +675,7 @@ {"batchId": "cf90bf18e1d046ddadc8968a623bf967", "completedAt": "2026-09-11T15:31:13.164650+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-11T15:30:57.117504+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6a206bff22bf42d298dbae81668fdd2c", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "reason": null, "reconciledAt": "2026-09-11T15:52:47.760611+00:00", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation"} {"batchId": "d5d8a922f1b942988202e0fdc139eda4", "completedAt": "2026-09-11T15:45:41.271246+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-11T15:45:33.425511+00:00", "framework": "vllm_tokenizer_patch", "intentId": "190b274e1b10409e8152fff5833030f0", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "reason": null, "reconciledAt": "2026-09-11T15:52:47.761246+00:00", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4782449", "taskType": "text-generation"} {"batchId": "f0c31a9d78274a05a8d63b12de111b9d", "completedAt": "2026-09-11T15:47:41.708955+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-11T15:47:33.464433+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c1b51ef2edd4a648576ee4dd6eec096", "lastModified": "2026-09-09T06:50:48+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "reason": null, "reconciledAt": "2026-09-11T15:52:47.760983+00:00", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "4782467", "taskType": "text-generation"} -{"batchId": "39789cb8c4c7440d8960964792a5409c", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-11T16:03:10.715055+00:00", "framework": "vllm-mlu", "intentId": "2a09ba9958f54909820f93b615b90b5d", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "39789cb8c4c7440d8960964792a5409c", "completedAt": "2026-09-11T16:03:38.536681+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-11T16:03:10.715055+00:00", "framework": "vllm-mlu", "intentId": "2a09ba9958f54909820f93b615b90b5d", "lastModified": "2026-09-11T15:37:46+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "reason": null, "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation"} {"batchId": "3cfa37416a9349629e882947d2816a4f", "completedAt": "2026-09-11T10:27:40.997245+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-11T10:27:32.517524+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "11684395861643dd8cc4c1610b8518a9", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "3cfa37416a9349629e882947d2816a4f", "completedAt": "2026-09-11T10:27:40.997200+00:00", "configFingerprint": "e57ef22c2d8b2b75e495765c383ba0c5b795fe18d7b7f1baf8dcfadd87065bd8", "configSource": "modelhub_live", "createdAt": "2026-09-11T10:27:32.516990+00:00", "framework": "llamacpp", "intentId": "a0656dc70ed9494580076f5910d1e348", "repoId": "TokenRhythm/NeoHorse-1-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"} {"batchId": "75d7acb27d704801b2ce084de0bf3900", "completedAt": "2026-09-11T02:14:19.417302+00:00", "configFingerprint": "3487754ba6ce87b4107d75c6476a4c5e5528f9179ac18665ecda0531c247da5e", "configSource": "modelhub_live", "createdAt": "2026-09-11T02:14:10.788042+00:00", "framework": "llamacpp", "intentId": "a31ea00fe3a847e6b52279c71b1fd09a", "repoId": "TokenRhythm/NeoHorse-1-4B-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 6e945cdf..b2267122 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 810 + "unified_success_first": 811 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 11, @@ -12,7 +12,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 28, "text-generation|Cambricon_mlu-370-x8|vllm": 13, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 1, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 67, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 68, "text-generation|Iluvatar_bi-150|llamacpp": 11, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 63, "text-generation|Iluvatar_mrv-100|vllm": 37, @@ -26,8 +26,8 @@ "text-generation|hygon_k100-ai|llamacpp": 11, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 45 }, - "acceptedSinceRefresh": 810, - "acceptedTotal": 810, - "generatedAt": "2026-09-11T15:47:41.682554+00:00", + "acceptedSinceRefresh": 811, + "acceptedTotal": 811, + "generatedAt": "2026-09-11T16:03:38.510573+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index c048c111..c360d0ee 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -767,3 +767,4 @@ {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T15:58:20.200513+00:00", "targetGpu": "Vastai_va16", "taskId": "4722293", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} {"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-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T16:03:11.891697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 32014ccf..aa6aa245 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "aef9d56345e6e6b2c6e9bcc5c224abe9dc0699f57e994e20e663ac3e21dd4b56", ".modelhub_state/recent_outcomes.jsonl": "120eccf9fa38b19d315a7cd6d5484fed6a29bc5c3a6301a857e192af6e539172", ".modelhub_state/recovery_active_tasks.jsonl": "b707c99c5455d846c121a5ada35db68728ee48d507cb940599f2db98d437e8d9", - ".modelhub_state/recovery_intents.jsonl": "12c4ccaae9509660d12816cb630534156be5af1fb342f8bc715b67f74fe5effe", - ".modelhub_state/routing_intelligence.json": "71d828155133d6d68c5d197bc27da626a7762e03d14928f26f9fc3c7a62a5118", + ".modelhub_state/recovery_intents.jsonl": "c018bd3041a8279338c5264a0d224c37d390393184995a0ae093fde233573635", + ".modelhub_state/routing_intelligence.json": "45cd0de22172f8254e5ec430826337eb427cc560fcf75d853fbe8e91d99de277", ".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89", ".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba", - "ledger/submissions.jsonl": "52cbfa28fd04dcc168ff647a5705bb1e30ca3ffefdd92b7b0a535fecb76708c4", - "outcomes/submissions.jsonl": "65b3a2b8b056962b55ccf1f3db2924ca378ac2a7d7eed538b37e687c974801c6" + "ledger/submissions.jsonl": "7586268a72b0ea3386909e187065b7f26ed7db7040d5138f4f9405021731e139", + "outcomes/submissions.jsonl": "c3b28e9ba34674de135b7b196b5a0a3aef97b3e40c8ed92febbebcb257e256da" }, - "generation": 5762, - "phase": "intent", + "generation": 5763, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-11T16:03:10.778450+00:00", + "updatedAt": "2026-09-11T16:03:38.595867+00:00", "writerId": "18252d8a8ef94333abd55823b2d81c42" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 46d0ab1d..caddba27 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -607,3 +607,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T15:30:58.007700+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T15:45:34.084559+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782449", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T15:47:34.151696+00:00", "targetGpu": "Vastai_va16", "taskId": "4782467", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T16:03:11.891697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation", "verifyResult": null}