From 887f2331730d88c683a12cc4e15dc42c4caac837 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Thu, 1 Oct 2026 06:18:00 +0000 Subject: [PATCH] state: generation 19101 (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 bb70bf672..f7522bcca 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2597,7 +2597,7 @@ {"batchId": "c4615b8c070a44b08e0db1c00e6552d6", "completedAt": "2026-10-01T05:41:59.519784+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-01T05:40:34.169188+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f9b5eb43b4314e80b563519a6e72fa1d", "lastModified": "2026-10-01T05:29:53+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6-4B-JANG_4M", "reason": null, "reconciledAt": "2026-10-01T06:05:42.676195+00:00", "repoId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation"} {"batchId": "6e89b295ee56455dbdfa2669572dd618", "completedAt": "2026-10-01T05:59:47.406261+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-01T05:57:46.290086+00:00", "framework": "vllm_tokenizer_patch", "intentId": "652c6718ae794338878a318fd722d27c", "lastModified": "2026-10-01T05:45:00+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "reason": null, "reconciledAt": "2026-10-01T06:05:42.677561+00:00", "repoId": "shisa-ai/shisa-de-1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation"} {"batchId": "f08085dbcdaf4177a4af5beaf5dd26f2", "completedAt": "2026-10-01T06:01:56.204475+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-01T06:01:53.981886+00:00", "framework": "vllm_tokenizer_patch", "intentId": "12fac27052884855b46af55bafb94ec0", "lastModified": "2026-10-01T05:29:53+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6-4B-JANG_4M", "reason": null, "reconciledAt": "2026-10-01T06:05:42.677031+00:00", "repoId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation"} -{"batchId": "221eb374b2d14937a0e691911a0a718d", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-10-01T06:15:51.690018+00:00", "framework": "vllm", "intentId": "0a1837cf7697494a87e053c0c641fa4c", "lastModified": "2026-10-01T05:45:00+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-1-FP8-dynamic", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "221eb374b2d14937a0e691911a0a718d", "completedAt": "2026-10-01T06:18:00.004603+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-10-01T06:15:51.690018+00:00", "framework": "vllm", "intentId": "0a1837cf7697494a87e053c0c641fa4c", "lastModified": "2026-10-01T05:45:00+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "reason": null, "repoId": "shisa-ai/shisa-de-1-FP8-dynamic", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "af702292a17240468562311292c55106", "completedAt": "2026-09-29T11:50:56.209408+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-29T11:50:53.929909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c488d875b85a4d699fe135674c2b940b", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 8833ebdff..4c5c3dc88 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,13 +1,13 @@ { "acceptedByCategory": { - "unified_success_first": 2736 + "unified_success_first": 2737 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 19, "text-generation|Ascend_910-b3|vllm": 40, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 181, "text-generation|Ascend_910-b4|llamacpp": 16, - "text-generation|Ascend_910-b4|vllm": 32, + "text-generation|Ascend_910-b4|vllm": 33, "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 210, "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 149, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2736, - "acceptedTotal": 2736, - "generatedAt": "2026-10-01T06:01:56.157241+00:00", + "acceptedSinceRefresh": 2737, + "acceptedTotal": 2737, + "generatedAt": "2026-10-01T06:17:59.955405+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 40f9bb9ed..08a95314f 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -963,3 +963,4 @@ {"framework": "transformers", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-transformers-iluvatar-bi-150"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:01:50.847636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5097139", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-09-26T08:18:32.495861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5097281", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} +{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index 9a14aee54..df297f7c2 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "05a1b3ebbbe8095e2f42ed6517a8c002726299deda90003a645472de6c83714e", ".modelhub_state/recent_outcomes.jsonl": "73f23566b5b4b8c0176d6e15dac2ca91200b082f28f05f39862b89485e9e092d", ".modelhub_state/recovery_active_tasks.jsonl": "edfa866b8374a1d71a0496279106ffa3591f0791180ea63ec8fc911a22d98773", - ".modelhub_state/recovery_intents.jsonl": "33cc70ce08fe672fecdade6cd13774ac19ff028414288dc306cb365b8aca5a22", - ".modelhub_state/routing_intelligence.json": "87f5ede50d7c43b223984d5eb6a7940fe9ccba1a522b74a596add95fe814abdc", + ".modelhub_state/recovery_intents.jsonl": "496d0ea81dd8e26cdc81098371e9b1faf1053190a45aafdfe1085aaebff8050c", + ".modelhub_state/routing_intelligence.json": "1b57ceab4c8d353e140012683aca39b2423393bd05a2d902e1c194a12397923d", ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c", ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd", - "ledger/submissions.jsonl": "884e1bcdac27017f09fc9b22a0650907a27305937af762b520d572d8c35663bf", - "outcomes/submissions.jsonl": "f7c86f147f7bdcfa5ed0fb1b82a46eb70c56e39ab595764bf24d002223f01823" + "ledger/submissions.jsonl": "ee9f67ef8ca359fc8d7675620c55bbefbf2b0529f2f2a6c49481771ac4e67620", + "outcomes/submissions.jsonl": "95eee77c624905c789d4eed741bed180c17254e0b407e10e55b0ce73b27fb709" }, - "generation": 19100, - "phase": "intent", + "generation": 19101, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-10-01T06:15:51.872575+00:00", + "updatedAt": "2026-10-01T06:18:00.117248+00:00", "writerId": "a812d0e025c3474eb16b828a4d987334" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index a866b1035..86bd15565 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -755,3 +755,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T05:41:58.050597+00:00", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "verifyResult": null}