From 94b97bd518a6c203dfdd3f7abbca4dd5bb975f93 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Wed, 30 Sep 2026 17:56:24 +0000 Subject: [PATCH] state: generation 18876 (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 1032c1bf41..017544ae42 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2583,7 +2583,7 @@ {"batchId": "6254218f420c415c99f2d4a58679a7b9", "completedAt": "2026-09-30T01:11:22.900449+00:00", "configFingerprint": "a46e54dca204d72badbcd6c046046d9ae760e08f88ce750e4e952731ff988fce", "configSource": "modelhub_live", "createdAt": "2026-09-30T01:09:02.975498+00:00", "framework": "llamacpp", "intentId": "accdc4e193ff47afad69503eed6ef468", "lastModified": "2026-09-09T18:56:44+00:00", "modelAddress": "https://modelscope.cn/models/DevQuasar/openbmb.MiniCPM5-2B-GGUF", "reason": null, "reconciledAt": "2026-09-30T17:53:26.687762+00:00", "repoId": "DevQuasar/openbmb.MiniCPM5-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5180739", "taskType": "text-generation"} {"batchId": "c1202a92bda64231a47deeb45528ff03", "completedAt": "2026-09-30T06:48:38.093682+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-30T06:46:23.175548+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ca8085aea8454300a222829d86f958a1", "lastModified": "2026-09-30T06:37:55+00:00", "modelAddress": "https://modelscope.cn/models/bytkim/Qwen3.8-27B-pi", "reason": null, "reconciledAt": "2026-09-30T17:53:26.687270+00:00", "repoId": "bytkim/Qwen3.8-27B-pi", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5185957", "taskType": "text-generation"} {"batchId": "111d8e02927f4a80938080b37cecadfc", "completedAt": "2026-09-30T17:39:07.002551+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-30T17:37:00.282969+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e6bcad3c04b4495b552992ad06b2a2b", "lastModified": "2026-09-30T17:34:11+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-5bit", "reason": null, "reconciledAt": "2026-09-30T17:53:26.687253+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5199381", "taskType": "text-generation"} -{"batchId": "02bdf6030b104a8eaa44cf2a3ed9315f", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T17:56:19.373715+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8bef664976f4457b8e79209f859d63fc", "lastModified": "2026-09-30T17:34:11+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-5bit", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "02bdf6030b104a8eaa44cf2a3ed9315f", "completedAt": "2026-09-30T17:56:23.997773+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-30T17:56:19.373715+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8bef664976f4457b8e79209f859d63fc", "lastModified": "2026-09-30T17:34:11+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-5bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "safeConfigVector": {"gpuNum": 1}, "status": "submitted", "targetGpu": "Ascend_910-b4", "taskId": "5199635", "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 dce9e877e3..5e21ca11dc 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 2722 + "unified_success_first": 2723 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 19, @@ -8,7 +8,7 @@ "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_tokenizer_patch": 205, + "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 206, "text-generation|Biren_166m|vllm": 81, "text-generation|Biren_166m|vllm_fix_tokenizer": 149, "text-generation|Cambricon_mlu-370-x4|vllm": 73, @@ -39,8 +39,8 @@ "text-generation|hygon_k100-ai|vllm": 27, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 152 }, - "acceptedSinceRefresh": 2722, - "acceptedTotal": 2722, - "generatedAt": "2026-09-30T17:39:06.958696+00:00", + "acceptedSinceRefresh": 2723, + "acceptedTotal": 2723, + "generatedAt": "2026-09-30T17:56:23.949532+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index b1f2ae06fa..e33d4ce4ba 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -973,3 +973,4 @@ {"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_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "submitTime": "2026-09-30T17:56:22.153029+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5199635", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} diff --git a/manifest.json b/manifest.json index 2e92b6b835..e2beec62ea 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "c1930ca8fdcacb5490295c7c7dc06f8ef1bd9c45953bf68d684e316cf0b931fd", ".modelhub_state/recent_outcomes.jsonl": "0ab1d5c5cfd855068e4f18ef6f8e3076175a93fcf632e662039eca492632e3b0", ".modelhub_state/recovery_active_tasks.jsonl": "33eac866de06690f0eb74d5bce2eaa807bc1241e8f58e96c0f1e66c962338087", - ".modelhub_state/recovery_intents.jsonl": "9a5298f09b522b73c0b21fcb7988a4483e876ccf1bfdde0d153091b6c0c3b07a", - ".modelhub_state/routing_intelligence.json": "1def34831f289200287ea373bacdccff4edac72941fcdbc5391d0d0585faab57", + ".modelhub_state/recovery_intents.jsonl": "c27ba124f53b519cea49c62efe20dd3e44cdb075c246df1ecdd7127a625b24d2", + ".modelhub_state/routing_intelligence.json": "e8424cdb344e0249188935c100d7be5c178326eab15b3d0df7ad2d21522df5d3", ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c", ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd", - "ledger/submissions.jsonl": "d74ca7b1471c86142486cc2432bf007f1b00dcb06e9710bd5ffef684d50d60f7", - "outcomes/submissions.jsonl": "38bb23fbbb35e395105065310d0402c39d597fe1c6d1d21f06e95c2599de6c9e" + "ledger/submissions.jsonl": "80d2a9cb2a466185f6f000644b415bcaa38c93c374b015b9ff1557fc62c9085f", + "outcomes/submissions.jsonl": "7067197c18484c2318682c138afcac41721482df4084515d46f3e1ac8748aff5" }, - "generation": 18875, - "phase": "intent", + "generation": 18876, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-30T17:56:19.564918+00:00", + "updatedAt": "2026-09-30T17:56:24.103511+00:00", "writerId": "a812d0e025c3474eb16b828a4d987334" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index ad2258ddca..df4928a22b 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -759,3 +759,4 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-30T09:21:23.144464+00:00", "modelId": "DevQuasar/openbmb.MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a46e54dca204d72badbcd6c046046d9ae760e08f88ce750e4e952731ff988fce", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712704, "estimatedRequiredGiB": 11.68, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10450678027, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10450678027}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T01:11:22.648777+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5180739", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-30T14:58:16.546919+00:00", "modelId": "bytkim/Qwen3.8-27B-pi", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 59411825056, "estimatedRequiredGiB": 66.425, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:speculative-decoding", "custom_tag:vision", "custom_tag:image", "custom_tag:multimodal", "custom_tag:image-text-to-text", "custom_tag:text-generation-inference", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:qwen38", "custom_tag:27b", "custom_tag:pi", "custom_tag:coding", "custom_tag:coder", "custom_tag:code-generation", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:reasoning", "custom_tag:conversational", "custom_tag:sft", "custom_tag:grpo", "custom_tag:reinforcement-learning", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 59435671311}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T06:48:36.947934+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5185957", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T17:39:03.747924+00:00", "targetGpu": "MetaX_c-500", "taskId": "5199381", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-30T17:56:22.153029+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5199635", "taskType": "text-generation", "verifyResult": null}