state: generation 6482 (cycle)
This commit is contained in:
@@ -1450,7 +1450,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T02:46:03.073485+00:00",
|
||||
"generatedAt": "2026-09-13T02:48:45.961733+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 73,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
"2": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 469,
|
||||
"listingErrors": 470,
|
||||
"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": 2,
|
||||
"nextAccountIndex": 3,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-13T02:46:03.049042+00:00",
|
||||
"updatedAt": "2026-09-13T02:48:45.938585+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T02:43:58.542913+00:00",
|
||||
"generatedAt": "2026-09-13T02:47:10.018262+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T02:29:19.435394+00:00",
|
||||
"lastSyncTime": "2026-09-13T02:29:19.214762+00:00",
|
||||
"generatedAt": "2026-09-13T02:47:04.270444+00:00",
|
||||
"lastSyncTime": "2026-09-13T02:47:03.906686+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1937,7 +1937,7 @@
|
||||
"decisionSuccessRate": 0.1333,
|
||||
"decisionTotal": 105,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 20,
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 49,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 41,
|
||||
@@ -1945,18 +1945,18 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 161,
|
||||
"failureRate": 0.92,
|
||||
"failureCount": 162,
|
||||
"failureRate": 0.9205,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 14,
|
||||
"successRate": 0.08,
|
||||
"successRate": 0.0795,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 175,
|
||||
"unresolvedFailureCount": 69
|
||||
"total": 176,
|
||||
"unresolvedFailureCount": 70
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -2464,7 +2464,7 @@
|
||||
"decisionSuccessRate": 0.2624,
|
||||
"decisionTotal": 202,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 138,
|
||||
"ambiguous_runtime": 139,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 94,
|
||||
"memory_capacity": 5,
|
||||
@@ -2474,15 +2474,15 @@
|
||||
"参数/模板问题": 59,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1020,
|
||||
"failureRate": 0.9506,
|
||||
"failureCount": 1021,
|
||||
"failureRate": 0.9507,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 53,
|
||||
"successRate": 0.0494,
|
||||
"total": 1073,
|
||||
"unresolvedFailureCount": 870
|
||||
"successRate": 0.0493,
|
||||
"total": 1074,
|
||||
"unresolvedFailureCount": 871
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 290,
|
||||
@@ -2613,7 +2613,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T02:29:19.430755+00:00",
|
||||
"generatedAt": "2026-09-13T02:47:04.265926+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 30,
|
||||
@@ -2782,7 +2782,7 @@
|
||||
"decisionSuccessRate": 0.1308,
|
||||
"decisionTotal": 107,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 20,
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 50,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 42,
|
||||
@@ -2790,15 +2790,15 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 163,
|
||||
"failureRate": 0.9209,
|
||||
"failureCount": 164,
|
||||
"failureRate": 0.9213,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 14,
|
||||
"successRate": 0.0791,
|
||||
"total": 177,
|
||||
"unresolvedFailureCount": 69
|
||||
"successRate": 0.0787,
|
||||
"total": 178,
|
||||
"unresolvedFailureCount": 70
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4670,22 +4670,22 @@
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 14,
|
||||
"attributableFailureCount": 13,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.7778,
|
||||
"decisionSuccessRate": 0.2222,
|
||||
"decisionTotal": 18,
|
||||
"decisionFailureRate": 0.7647,
|
||||
"decisionSuccessRate": 0.2353,
|
||||
"decisionTotal": 17,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 13
|
||||
"model_load": 12
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 0.8,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T21:28:41.303467+00:00",
|
||||
"lastTerminalAt": "2026-09-13T02:47:03.906686+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4694,7 +4694,7 @@
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 2
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7362,15 +7362,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1752,
|
||||
"totalRecords": 1839,
|
||||
"terminalRecords": 1753,
|
||||
"totalRecords": 1840,
|
||||
"totals": {
|
||||
"attributableFailureCount": 505,
|
||||
"decisionFailureRate": 0.897,
|
||||
"decisionSuccessRate": 0.103,
|
||||
"decisionTotal": 563,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 411,
|
||||
"ambiguous_runtime": 412,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 317,
|
||||
"memory_capacity": 11,
|
||||
@@ -7382,20 +7382,21 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1694,
|
||||
"failureCount": 1695,
|
||||
"failureRate": 0.9669,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 58,
|
||||
"successRate": 0.0331,
|
||||
"total": 1752,
|
||||
"unresolvedFailureCount": 1185
|
||||
"total": 1753,
|
||||
"unresolvedFailureCount": 1186
|
||||
},
|
||||
"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。",
|
||||
@@ -7404,7 +7405,6 @@
|
||||
"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。",
|
||||
@@ -7427,6 +7427,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1839,
|
||||
"summarizedRecords": 1840,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T02:47:03.906686+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549639", "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": "2026-09-13T02:20:50.802489+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:13:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4549809", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:12:14.114155+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:09:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4543931", "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": "2026-09-13T02:12:14.114179+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4543902", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-09T04:51:59.603427+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T04:51:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332977", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T04:15:14.005422+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T04:13:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471924", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T03:27:28.006277+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T03:27:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4081077", "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": "2026-09-09T01:26:01.901607+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T01:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079158", "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