From b0250bf0ffef70759c4a9c9db5fc4336e73ea798 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Thu, 10 Sep 2026 07:23:17 +0000 Subject: [PATCH] state: generation 5046 (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 09ae2b19..b5b9f706 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -629,7 +629,7 @@ {"batchId": "f9e866c67cf14708a87905c2954924e8", "completedAt": "2026-09-10T07:12:35.485224+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:12:25.475050+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8945eab9071640ba9f69f93ea9980dc8", "lastModified": "2026-09-10T05:34:35+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "reason": null, "reconciledAt": "2026-09-10T07:14:43.858978+00:00", "repoId": "primitive-ai/Nex-N2.5-mini-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation"} {"batchId": "f9e866c67cf14708a87905c2954924e8", "completedAt": "2026-09-10T07:12:35.485227+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:12:25.475094+00:00", "framework": "vllm_fix_tokenizer", "intentId": "813fe280cbf54ca9ad8ef162cc185d0f", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T07:14:43.857441+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation"} {"batchId": "f9e866c67cf14708a87905c2954924e8", "completedAt": "2026-09-10T07:12:35.485229+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:12:25.475137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3e8d3bcf62af4f8cbc19db016bbdd397", "lastModified": "2026-08-11T14:42:47+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "reason": null, "reconciledAt": "2026-09-10T07:14:43.858628+00:00", "repoId": "BAAI/AREX-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation"} -{"batchId": "9a95cae7b6614130bf9c1de89e7e18e6", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:23:09.465940+00:00", "framework": "vllm-mlu", "intentId": "5253cbeaf413435a975f178c59c5b615", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"} +{"batchId": "9a95cae7b6614130bf9c1de89e7e18e6", "completedAt": "2026-09-10T07:23:17.487528+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-10T07:23:09.465940+00:00", "framework": "vllm-mlu", "intentId": "5253cbeaf413435a975f178c59c5b615", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation"} {"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} {"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json index affe96bf..3fdd31d8 100644 --- a/.modelhub_state/routing_intelligence.json +++ b/.modelhub_state/routing_intelligence.json @@ -1,6 +1,6 @@ { "acceptedByCategory": { - "unified_success_first": 764 + "unified_success_first": 765 }, "acceptedByRoute": { "text-generation|Ascend_910-b3|llamacpp": 9, @@ -12,7 +12,7 @@ "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 26, "text-generation|Cambricon_mlu-370-x8|vllm": 13, "text-generation|Cambricon_mlu-370-x8|vllm-customized": 1, - "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 66, + "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 67, "text-generation|Iluvatar_bi-150|llamacpp": 10, "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 50, "text-generation|Iluvatar_mrv-100|vllm": 36, @@ -26,8 +26,8 @@ "text-generation|hygon_k100-ai|llamacpp": 9, "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 44 }, - "acceptedSinceRefresh": 764, - "acceptedTotal": 764, - "generatedAt": "2026-09-10T07:12:35.449944+00:00", + "acceptedSinceRefresh": 765, + "acceptedTotal": 765, + "generatedAt": "2026-09-10T07:23:17.452106+00:00", "version": 1 } diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl index 469baad8..ec23cfb8 100644 --- a/ledger/submissions.jsonl +++ b/ledger/submissions.jsonl @@ -724,3 +724,4 @@ {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"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-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} diff --git a/manifest.json b/manifest.json index 33fe5861..f5ceb153 100644 --- a/manifest.json +++ b/manifest.json @@ -9,16 +9,16 @@ ".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99", ".modelhub_state/recent_outcomes.jsonl": "3718ee3d75347a8064d7de596cfc5fa00b55b2d644f0295ed664d9c491d15d3a", ".modelhub_state/recovery_active_tasks.jsonl": "b89cab028fdd7d0efce9e12d5a1d92497aabb4dd4701e3bfeb9782037c48b876", - ".modelhub_state/recovery_intents.jsonl": "1d7e1b87d606a7539fd3a2b26694cc4db355bafcda29c146141c27c6b2549c96", - ".modelhub_state/routing_intelligence.json": "023995e82c8ed80a7c0a402b6b05c8d7ad07c2d81b1f3f5fd346e1b67a83fd22", + ".modelhub_state/recovery_intents.jsonl": "3d30099b8433c344f9bfcbc8b993f91608738b4700761e85e3114fe336cb43bf", + ".modelhub_state/routing_intelligence.json": "c3286852fe788ac5b6e6a51d221eeaf9c000146e6ee7c7de72b25fa6df6dc9a0", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", - "ledger/submissions.jsonl": "c2dc7a97a6a1ab972e2555984832fb68fcf119ef2185f821a36ce764f056f01f", - "outcomes/submissions.jsonl": "a0af90115ca496eb465397d8e7bb628d07231edb04cb36b863585be644474820" + "ledger/submissions.jsonl": "548d915740550052f86db5ab45dfc4559431ad8400748ab970001db035b6e49f", + "outcomes/submissions.jsonl": "3c13cb6ed6c4b6c6ce7aae4d921686e244aaba544f011a1187acf041e7db6858" }, - "generation": 5045, - "phase": "intent", + "generation": 5046, + "phase": "result", "schemaVersion": 1, - "updatedAt": "2026-09-10T07:23:09.537125+00:00", + "updatedAt": "2026-09-10T07:23:17.630204+00:00", "writerId": "58ff5dc2a2d64b119ad1e4560700f977" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index a3281c04..682ec816 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -593,3 +593,4 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "verifyResult": null}