state: generation 6036 (cycle)
This commit is contained in:
@@ -1345,7 +1345,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T04:57:36.481770+00:00",
|
||||
"generatedAt": "2026-09-12T05:00:22.664719+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 68,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 433,
|
||||
"listingErrors": 434,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-12T04:57:36.457472+00:00",
|
||||
"updatedAt": "2026-09-12T05:00:22.640176+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T04:56:07.896048+00:00",
|
||||
"generatedAt": "2026-09-12T04:58:44.470835+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T04:41:36.495853+00:00",
|
||||
"lastSyncTime": "2026-09-12T04:41:36.246914+00:00",
|
||||
"generatedAt": "2026-09-12T04:58:37.438591+00:00",
|
||||
"lastSyncTime": "2026-09-12T04:58:37.211400+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2286,19 +2286,19 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 37,
|
||||
"attributableFailureCount": 39,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 37,
|
||||
"decisionTotal": 39,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 28,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 3,
|
||||
"model_load": 4,
|
||||
"repository_structure": 4,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 53,
|
||||
"failureCount": 55,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2308,7 +2308,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 53,
|
||||
"total": 55,
|
||||
"unresolvedFailureCount": 16
|
||||
}
|
||||
},
|
||||
@@ -2377,30 +2377,30 @@
|
||||
"unresolvedFailureCount": 862
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 252,
|
||||
"decisionFailureRate": 0.9882,
|
||||
"decisionSuccessRate": 0.0118,
|
||||
"decisionTotal": 255,
|
||||
"attributableFailureCount": 254,
|
||||
"decisionFailureRate": 0.9883,
|
||||
"decisionSuccessRate": 0.0117,
|
||||
"decisionTotal": 257,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 174,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 21,
|
||||
"model_load": 22,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 6,
|
||||
"repository_structure": 7,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 6,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 472,
|
||||
"failureCount": 474,
|
||||
"failureRate": 0.9937,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0063,
|
||||
"total": 475,
|
||||
"total": 477,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2505,7 +2505,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T04:41:36.489015+00:00",
|
||||
"generatedAt": "2026-09-12T04:58:37.432031+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2811,28 +2811,28 @@
|
||||
"unresolvedFailureCount": 206
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 40,
|
||||
"attributableFailureCount": 42,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 40,
|
||||
"decisionTotal": 42,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 31,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 3,
|
||||
"model_load": 4,
|
||||
"repository_structure": 4,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 9,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 94,
|
||||
"failureCount": 96,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 94,
|
||||
"total": 96,
|
||||
"unresolvedFailureCount": 54
|
||||
}
|
||||
},
|
||||
@@ -4777,23 +4777,24 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"repository_structure": 1,
|
||||
"model_load": 1,
|
||||
"repository_structure": 2,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 19,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-11T21:18:30.415792+00:00",
|
||||
"lastTerminalAt": "2026-09-12T04:58:37.211377+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4801,7 +4802,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 12
|
||||
}
|
||||
},
|
||||
@@ -7240,40 +7241,41 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1685,
|
||||
"totalRecords": 1772,
|
||||
"terminalRecords": 1687,
|
||||
"totalRecords": 1774,
|
||||
"totals": {
|
||||
"attributableFailureCount": 457,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 513,
|
||||
"attributableFailureCount": 459,
|
||||
"decisionFailureRate": 0.8913,
|
||||
"decisionSuccessRate": 0.1087,
|
||||
"decisionTotal": 515,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 394,
|
||||
"backend_operator": 41,
|
||||
"framework_architecture_unsupported": 281,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 65,
|
||||
"model_load": 66,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 6,
|
||||
"repository_structure": 7,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 47,
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1629,
|
||||
"failureCount": 1631,
|
||||
"failureRate": 0.9668,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 56,
|
||||
"successRate": 0.0332,
|
||||
"total": 1685,
|
||||
"total": 1687,
|
||||
"unresolvedFailureCount": 1168
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7282,7 +7284,6 @@
|
||||
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7304,6 +7305,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1772,
|
||||
"summarizedRecords": 1774,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211377+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080069", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211400+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079952", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T04:41:36.246914+00:00", "modelId": "LLM-Research/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:35:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080064", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T03:32:35.805010+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080052", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937930+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080040", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -296,5 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T03:01:10.207494+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950378091, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322093+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:35:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080063", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322073+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:31:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080049", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322084+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:31:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080030", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322046+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080032", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user