state: generation 6491 (cycle)

This commit is contained in:
2026-09-13 03:14:45 +00:00
parent d0396d768a
commit 5475be0a36
9 changed files with 2028 additions and 2028 deletions

View File

@@ -1452,7 +1452,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T03:11:56.751958+00:00",
"generatedAt": "2026-09-13T03:14:44.819068+00:00",
"summary": {
"activeBlockCount": 73,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"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": 11,
"nextAccountIndex": 0,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-13T03:11:56.728771+00:00",
"updatedAt": "2026-09-13T03:14:44.796377+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T03:10:14.777826+00:00",
"generatedAt": "2026-09-13T03:13:09.213691+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T02:55:30.151645+00:00",
"lastSyncTime": "2026-09-13T02:55:29.910747+00:00",
"generatedAt": "2026-09-13T03:12:57.762588+00:00",
"lastSyncTime": "2026-09-13T03:12:57.550578+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1934,30 +1934,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 91,
"decisionFailureRate": 0.8667,
"decisionSuccessRate": 0.1333,
"decisionTotal": 105,
"attributableFailureCount": 92,
"decisionFailureRate": 0.8679,
"decisionSuccessRate": 0.1321,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 49,
"framework_architecture_unsupported": 50,
"memory_capacity": 1,
"model_load": 41,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 162,
"failureRate": 0.9205,
"failureCount": 163,
"failureRate": 0.9209,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 14,
"successRate": 0.0795,
"successRate": 0.0791,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 176,
"total": 177,
"unresolvedFailureCount": 70
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2461,14 +2461,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 149,
"decisionFailureRate": 0.7376,
"decisionSuccessRate": 0.2624,
"decisionTotal": 202,
"attributableFailureCount": 150,
"decisionFailureRate": 0.7389,
"decisionSuccessRate": 0.2611,
"decisionTotal": 203,
"failureBreakdown": {
"ambiguous_runtime": 139,
"backend_operator": 4,
"framework_architecture_unsupported": 94,
"framework_architecture_unsupported": 95,
"memory_capacity": 5,
"model_load": 43,
"platform_infrastructure": 1,
@@ -2476,14 +2476,14 @@
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1023,
"failureRate": 0.9507,
"failureCount": 1024,
"failureRate": 0.9508,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 53,
"successRate": 0.0493,
"total": 1076,
"successRate": 0.0492,
"total": 1077,
"unresolvedFailureCount": 873
},
"vllm": {
@@ -2615,7 +2615,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T02:55:30.147369+00:00",
"generatedAt": "2026-09-13T03:12:57.758640+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2779,27 +2779,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 93,
"decisionFailureRate": 0.8692,
"decisionSuccessRate": 0.1308,
"decisionTotal": 107,
"attributableFailureCount": 94,
"decisionFailureRate": 0.8704,
"decisionSuccessRate": 0.1296,
"decisionTotal": 108,
"failureBreakdown": {
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 50,
"framework_architecture_unsupported": 51,
"memory_capacity": 1,
"model_load": 42,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 164,
"failureRate": 0.9213,
"failureCount": 165,
"failureRate": 0.9218,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 14,
"successRate": 0.0787,
"total": 178,
"successRate": 0.0782,
"total": 179,
"unresolvedFailureCount": 70
},
"Kunlunxin_p-800": {
@@ -4673,21 +4673,21 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 1,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.7647,
"decisionSuccessRate": 0.2353,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 1,
"model_load": 12
"framework_architecture_unsupported": 2,
"model_load": 11
},
"failureCount": 16,
"failureRate": 0.8,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:47:03.906686+00:00",
"lastTerminalAt": "2026-09-13T03:12:57.550578+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7391,17 +7391,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1756,
"totalRecords": 1843,
"terminalRecords": 1757,
"totalRecords": 1844,
"totals": {
"attributableFailureCount": 506,
"decisionFailureRate": 0.8972,
"decisionSuccessRate": 0.1028,
"decisionTotal": 564,
"attributableFailureCount": 507,
"decisionFailureRate": 0.8973,
"decisionSuccessRate": 0.1027,
"decisionTotal": 565,
"failureBreakdown": {
"ambiguous_runtime": 412,
"backend_operator": 42,
"framework_architecture_unsupported": 318,
"framework_architecture_unsupported": 319,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7411,20 +7411,21 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1698,
"failureCount": 1699,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 58,
"successRate": 0.033,
"total": 1756,
"total": 1757,
"unresolvedFailureCount": 1188
},
"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。",
@@ -7433,7 +7434,6 @@
"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。",
@@ -7456,6 +7456,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1843,
"summarizedRecords": 1844,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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"], "framework": "", "lastSyncTime": "2026-09-13T03:12:57.550578+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549641", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910704+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133475", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910734+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "MetaX_c-500", "taskId": "4133144", "taskType": "text-generation", "verifyResult": null}
{"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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:55:29.910747+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4557197", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-09T05:56:37.494970+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:53:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471929", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T05:53:14.296748+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:51:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083446", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T05:15:37.097487+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:15:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591599", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T05:12:14.918874+00:00", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523219", "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