From c962fa379aa04172c3a2d5ce602e3fc1bcc8a28c Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 12:25:51 +0000 Subject: [PATCH] state: generation 11454 (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 85c69b70b5..70ffd47de2 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2091,7 +2091,7 @@ {"batchId": "8bafcb75d1c44e17bf33df9c6eb1b308", "completedAt": "2026-09-21T12:10:32.612386+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:10:24.304537+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c4a11aa60f1540d4a1ee912c55721e37", "lastModified": "2026-09-16T17:02:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-21T12:19:51.095678+00:00", "repoId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5000553", "taskType": "text-generation"} {"batchId": "8bafcb75d1c44e17bf33df9c6eb1b308", "completedAt": "2026-09-21T12:10:32.612389+00:00", "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:10:24.304577+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e92d0f0099ec4a1bbfaa0d06f9cd7ec6", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "reason": null, "reconciledAt": "2026-09-21T12:19:51.097908+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "5000550", "taskType": "text-generation"} {"batchId": "8bafcb75d1c44e17bf33df9c6eb1b308", "completedAt": "2026-09-21T12:10:32.612392+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:10:24.304616+00:00", "framework": "vllm-customized", "intentId": "e05cb29556ab4e878fa5b7f7ee9ba6fe", "lastModified": "2026-09-16T16:39:48+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/RoboBrain2.5-8B-MT", "reason": null, "reconciledAt": "2026-09-21T12:23:24.003849+00:00", "repoId": "BAAI/RoboBrain2.5-8B-MT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000548", "taskType": "text-generation"} -{"batchId": "84093a5315214302a808d0cf9f26c065", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:25:49.243062+00:00", "framework": "vllm-customized", "intentId": "633df8c09b3e44578455ef2c18a36fb1", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "84093a5315214302a808d0cf9f26c065", "completedAt": "2026-09-21T12:25:51.109238+00:00", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:25:49.243062+00:00", "framework": "vllm-customized", "intentId": "633df8c09b3e44578455ef2c18a36fb1", "lastModified": "2026-09-14T19:52:04+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "reason": null, "repoId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000706", "taskType": "text-generation"} {"batchId": "81ffde05d8a240e1b109fd37b11d04ee", "completedAt": "2026-09-21T12:09:46.211287+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:06:14.559672+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea3e3fb6fcad4b14b62d5deaeaf41d15", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "81ffde05d8a240e1b109fd37b11d04ee", "completedAt": "2026-09-21T12:09:46.211284+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:06:14.559612+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e91415b541d9406e9ffb97c34067156d", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} {"batchId": "81ffde05d8a240e1b109fd37b11d04ee", "completedAt": "2026-09-21T12:09:46.211281+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:06:14.559558+00:00", "framework": "vllm_fix_tokenizer", "intentId": "15c1a05a7c834dc8b817978153efb45b", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 22daaad4ff..a96a6f23c5 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2230 + "unified_success_first": 2231 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, @@ -15,7 +15,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-customized": 5, "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 85, "text-generation|Cambricon_mlu-370-x8|vllm": 55, - "text-generation|Cambricon_mlu-370-x8|vllm-customized": 66, + "text-generation|Cambricon_mlu-370-x8|vllm-customized": 67, "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 96, "text-generation|Iluvatar_bi-100|transformers": 20, "text-generation|Iluvatar_bi-150|llamacpp": 16, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 128 }, - "acceptedSinceRefresh": 2230, - "acceptedTotal": 2230, - "generatedAt": "2026-09-21T12:10:32.543979+00:00", + "acceptedSinceRefresh": 2231, + "acceptedTotal": 2231, + "generatedAt": "2026-09-21T12:25:51.048493+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 7738621184..f2a158382e 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1200,3 +1200,4 @@ {"framework": "vllm_tokenizer_patch", "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": "2026-09-21T12:10:32.436494+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000547", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-21T12:10:32.453427+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000553", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-21T12:10:32.435532+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000550", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-iluvatar-bi-150"} +{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-21T12:25:50.997483+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000706", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index fce24d03c0..7b9f060a42 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f056ed79dc68b93c34c77c843adbb41f111ead8321367e55fb184c2bf909b4b8", ".modelhub_state/recent_outcomes.jsonl": "547a04d8d65f244ddfe7587f83edc0672c6530bf217bc4d021930e6c200af0ac", ".modelhub_state/recovery_active_tasks.jsonl": "b0dbd2282aa92d8c682e63f3872fd0bb64c33bc6af978f3b8dcbe2557637fc5c", - ".modelhub_state/recovery_intents.jsonl": "536b47840645bba33e30e18438a60ffa1a492fb488ce356fe3d258d1af573a7e", - ".modelhub_state/routing_intelligence.json": "70102c117314452b6a1c062a39e8ceb56e6025538a6fd9194c7de23de05ae656", + ".modelhub_state/recovery_intents.jsonl": "7ae99687313519fc9480c14abc91726fa2f0e89284938f1efaee7abf0aefe75e", + ".modelhub_state/routing_intelligence.json": "b3d7d7efed95d0effb6f66876d5a51fafcff13b8a430b785ef555626d4d8a09b", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "031bfb45fd120facde919a99cf6205f3494e2587ae2d2ba7cbc0529c08546c39", - "outcomes/submissions.jsonl": "3b8b6f434eb4b0428b58c4638069942b5ee8a33061cc6fb9d51b896c0f172220" + "ledger/submissions.jsonl": "ac2d8e398d91faa7704aa63029a812790198a449039035a4a80c2c7092440f32", + "outcomes/submissions.jsonl": "9896955ae7fcbd537e6187e18758bf229fc47449325f04318ad939044ff26724" }, - "generation": 11453, - "phase": "intent", + "generation": 11454, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T12:25:49.431707+00:00", + "updatedAt": "2026-09-21T12:25:51.241199+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index ad3c252b31..b92f559adc 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1142,3 +1142,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:10:32.453427+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000553", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"model_load": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T04:36:00.569307+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 663396475}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:10:32.435532+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000550", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "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": 17545918174}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:10:32.405767+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000548", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:25:50.997483+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5000706", "taskType": "text-generation", "verifyResult": null}