From f14ea22f195d9ae5cc9734446334cc7e89857198 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sat, 12 Sep 2026 16:59:24 +0000 Subject: [PATCH] state: generation 6289 (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 600fde22..5b6b5651 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -702,7 +702,7 @@ {"batchId": "391e4ecca6f542499c867a883bd0242b", "completedAt": "2026-09-12T10:59:05.609717+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-12T10:58:56.015906+00:00", "framework": "vllm_fix_tokenizer", "intentId": "12c84c4f7ec241a1bfdafb2a7a975997", "lastModified": "2026-08-12T22:21:26+00:00", "modelAddress": "https://modelscope.cn/models/unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "reason": null, "reconciledAt": "2026-09-12T16:49:34.542507+00:00", "repoId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation"} {"batchId": "74247e1dc50b46c6afe5734926612a42", "completedAt": "2026-09-12T14:10:00.331519+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-12T14:09:51.658347+00:00", "framework": "vllm", "intentId": "bf3b6e3c037a42cd9f1dac23d1708d0d", "lastModified": "2026-08-23T05:35:28+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "reason": null, "reconciledAt": "2026-09-12T16:49:34.542330+00:00", "repoId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation"} {"batchId": "573ab73eda4e4ddcbbf93cef632e7935", "completedAt": "2026-09-12T16:07:27.541576+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-12T16:07:20.878629+00:00", "framework": "vllm", "intentId": "6a9c174b1c6c441a9372f9a0ecb04216", "lastModified": "2026-08-23T05:35:28+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "reason": null, "reconciledAt": "2026-09-12T16:49:34.542127+00:00", "repoId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation"} -{"batchId": "1f156678e1bf4a7684cdde06dbd20201", "configFingerprint": "c21a8c5b2598ee6aec1301e1dba618e3f68c70a7ab35b6b215134aa6e6b9a3eb", "configSource": "modelhub_live", "createdAt": "2026-09-12T16:59:16.346173+00:00", "framework": "llamacpp", "intentId": "d915fed2056f4d7498ae9c900b770a76", "lastModified": "2026-09-07T06:55:52+00:00", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "repoId": "cloudlnk/Spark-X2.5-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "1f156678e1bf4a7684cdde06dbd20201", "completedAt": "2026-09-12T16:59:24.136777+00:00", "configFingerprint": "c21a8c5b2598ee6aec1301e1dba618e3f68c70a7ab35b6b215134aa6e6b9a3eb", "configSource": "modelhub_live", "createdAt": "2026-09-12T16:59:16.346173+00:00", "framework": "llamacpp", "intentId": "d915fed2056f4d7498ae9c900b770a76", "lastModified": "2026-09-07T06:55:52+00:00", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "reason": null, "repoId": "cloudlnk/Spark-X2.5-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation"} {"batchId": "3d8ea5cfb1b4463186deaecd57181439", "completedAt": "2026-09-11T18:18:45.233173+00:00", "configFingerprint": "2cf5058acf9c5bb823914c7d9c505e7d3654b96e77d3349ed68eaec1f5014ac7", "configSource": "modelhub_live", "createdAt": "2026-09-11T18:18:26.469097+00:00", "framework": "llamacpp", "intentId": "52dcd9c431d54a84a0ae32dcc47745f2", "repoId": "TokenRhythm/NeoHorse-1-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "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"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index 3d8cd604..72d6cb67 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 837 + "unified_success_first": 838 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 11, @@ -23,11 +23,11 @@ "text-generation|Sunrise_pt-200-x1|vllm": 56, "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 50, "text-generation|Vastai_va16|vllm_fix_tokenizer": 38, - "text-generation|hygon_k100-ai|llamacpp": 11, + "text-generation|hygon_k100-ai|llamacpp": 12, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 47 }, - "acceptedSinceRefresh": 837, - "acceptedTotal": 837, - "generatedAt": "2026-09-12T16:07:27.505589+00:00", + "acceptedSinceRefresh": 838, + "acceptedTotal": 838, + "generatedAt": "2026-09-12T16:59:24.097870+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index e41b5eb5..25573533 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -786,3 +786,4 @@ {"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": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"} diff --git a/manifest.json b/manifest.json index 26b86854..f23a581e 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "ccebc58971e155e7d5987315af83d23359f4ad65134945945f168235fb97bc19", ".modelhub_state/recent_outcomes.jsonl": "d6fdf7c9bf00ecb23b23c259ca5972bd4f5a05967c9f7e703823bd203573b79d", ".modelhub_state/recovery_active_tasks.jsonl": "59367d74e391f593ba21c1b62fd3957d4b2a4be298e71fedf43d5687882e6c7b", - ".modelhub_state/recovery_intents.jsonl": "695d97a58930008eba15822a84532611ca8a1b868458f4e4bc0e504a9b94dcb5", - ".modelhub_state/routing_intelligence.json": "c93e82912b7f1d2456dce64bf91c49e9109a7e4fba751ceb4367855555cf48a1", + ".modelhub_state/recovery_intents.jsonl": "1a342d93cd933826fe20f44d0212e6a7bfecd9290d3773af8c5168c5d9f6a5da", + ".modelhub_state/routing_intelligence.json": "8ea9462ebc56340d03024023dbe9214e5813e601e8e81ed82f8d0d04aaacc292", ".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220", ".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162", - "ledger/submissions.jsonl": "704401797a202ff5babd19cb7f0f95713518fcb0fc9263f459e616b192d2a2ad", - "outcomes/submissions.jsonl": "67bfefc7ff455a885e6ceeafbeec795f7f2ef55b8ec61a8472a4c8a0686448bc" + "ledger/submissions.jsonl": "70cb88d11031790cd80ff489377db68b5491a257415faf621146e688aeb2a23c", + "outcomes/submissions.jsonl": "b12883e91f558e5e088a95cf24fc17d44a55c882fb897f4c415817559c217dd3" }, - "generation": 6288, - "phase": "intent", + "generation": 6289, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-12T16:59:16.423572+00:00", + "updatedAt": "2026-09-12T16:59:24.254829+00:00", "writerId": "e5dd59a4c84a4f21926bad61448789e2" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index c29aba37..21a0f75f 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -628,3 +628,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c21a8c5b2598ee6aec1301e1dba618e3f68c70a7ab35b6b215134aa6e6b9a3eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "verifyResult": null}