From b2d82db1cac905c295f815e52ef5f6ebb18b8c90 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 13:01:29 +0000 Subject: [PATCH] state: generation 11464 (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 1bd1deae92..2f0494b32d 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2104,7 +2104,7 @@ {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291967+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267848+00:00", "framework": "vllm", "intentId": "6f421226cfb54296a0542d8b0ed46b6a", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "reason": null, "reconciledAt": "2026-09-21T12:58:47.852873+00:00", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5001062", "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291970+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267906+00:00", "framework": "vllm", "intentId": "74da361d638e4e30932524ccdf826191", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "reason": null, "reconciledAt": "2026-09-21T12:58:47.851560+00:00", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5001063", "taskType": "text-generation"} {"batchId": "62c41e3a73cd487f80e78f240705c764", "completedAt": "2026-09-21T12:54:38.291972+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:48:53.267963+00:00", "framework": "vllm", "intentId": "13bf4cfa6dfb4d309aa8f8e94b2c4168", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "reason": null, "reconciledAt": "2026-09-21T12:58:47.854410+00:00", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5001061", "taskType": "text-generation"} -{"batchId": "c37e6d2ae344408f97e8141be13469ad", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:01:19.328360+00:00", "framework": "vllm", "intentId": "8c20c9ea6120403fac51e2f59ddb9f4f", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "c37e6d2ae344408f97e8141be13469ad", "completedAt": "2026-09-21T13:01:29.014237+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T13:01:19.328360+00:00", "framework": "vllm", "intentId": "8c20c9ea6120403fac51e2f59ddb9f4f", "lastModified": "2026-09-16T17:07:54+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "reason": null, "repoId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Ascend_910-b3", "taskId": "5001186", "taskType": "text-generation"} {"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "completedAt": "2026-09-21T12:58:46.473061+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.200080+00:00", "framework": "vllm", "intentId": "7b95fa300bf44f589a7807314d2d6cf8", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "completedAt": "2026-09-21T12:58:46.473058+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.200021+00:00", "framework": "vllm", "intentId": "e0c7ac7008394ef58e4332e57fa44ec4", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} {"batchId": "9cb2439dc27a4294ba6fc5cd6afe80f3", "completedAt": "2026-09-21T12:58:46.473055+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T12:54:39.199961+00:00", "framework": "vllm", "intentId": "69ca6ed0cf9747119b2d008deb762358", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index fb1760a7e5..c1810175a1 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,10 +1,10 @@ { "acceptedByCategory": { - "unified_success_first": 2243 + "unified_success_first": 2244 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 17, - "text-generation|Ascend_910-b3|vllm": 38, + "text-generation|Ascend_910-b3|vllm": 39, "text-generation|Ascend_910-b3|vllm_tokenizer_patch": 158, "text-generation|Ascend_910-b4|llamacpp": 13, "text-generation|Ascend_910-b4|vllm": 27, @@ -38,8 +38,8 @@ "text-generation|hygon_k100-ai|vllm": 26, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 128 }, - "acceptedSinceRefresh": 2243, - "acceptedTotal": 2243, - "generatedAt": "2026-09-21T12:58:46.401416+00:00", + "acceptedSinceRefresh": 2244, + "acceptedTotal": 2244, + "generatedAt": "2026-09-21T13:01:28.952132+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 9424954c7a..0a52db4555 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -1202,3 +1202,4 @@ {"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", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "submitTime": "2026-09-21T13:01:28.899242+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5001186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"} diff --git a/manifest.json b/manifest.json index 07ce9bdd7f..82ca2679a8 100644 --- a/manifest.json +++ b/manifest.json @@ -10,16 +10,16 @@ ".modelhub_state/queue_cleanup_latest.json": "f056ed79dc68b93c34c77c843adbb41f111ead8321367e55fb184c2bf909b4b8", ".modelhub_state/recent_outcomes.jsonl": "2455cee796e8cc371207f7dea53056902bb7235b9126cb92c937acaeffa8ae03", ".modelhub_state/recovery_active_tasks.jsonl": "e7e11d96613f5ccb4849f6930a6db9fc7f69449e3db29e104289ebf33a4833df", - ".modelhub_state/recovery_intents.jsonl": "82b25dd712224c257bc1e20dd2d2e0efc082f7214c6e9fe2470d5254a77b1eaf", - ".modelhub_state/routing_intelligence.json": "909b8f39789653248c3b1ce1078e10aba240486ccdbc1970d7b0a6f857a3c7a9", + ".modelhub_state/recovery_intents.jsonl": "5490d568a7816c2ad90d6778e0f1acdfd7b5ff8b88ca0392a6b78705adeaa389", + ".modelhub_state/routing_intelligence.json": "8b64012e7933a3ad7713b72ea4c963ce31c8db8a445ca48b594e6b595e2433e0", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", - "ledger/submissions.jsonl": "c20139912f124d981c5a9718a2cc91da53e26aa110d259de27609a8703977e54", - "outcomes/submissions.jsonl": "71436f16ff9fef8f8cf3f23aef75e93ce05d59e3de78fb84dd00d829a0e6a9aa" + "ledger/submissions.jsonl": "a392256d1d923f4ec65859ae66c28e3991a481bbb99608818e0c961c67a87ada", + "outcomes/submissions.jsonl": "1536baf7059972a81e520041a090ecc3fcb311872e37a2d2360700d238474bc0" }, - "generation": 11463, - "phase": "intent", + "generation": 11464, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-21T13:01:19.542527+00:00", + "updatedAt": "2026-09-21T13:01:29.138818+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 0f434416b8..91be1adaf0 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1145,3 +1145,4 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:49:01.237142+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001062", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:49:01.244975+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001063", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T12:49:01.249214+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001061", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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": 955857175}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T13:01:28.899242+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5001186", "taskType": "text-generation", "verifyResult": null}