state: generation 5947 (cycle)

This commit is contained in:
2026-09-12 00:54:03 +00:00
parent 359c411dca
commit ad256315fa
10 changed files with 2079 additions and 2079 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T00:50:59.516991+00:00",
"generatedAt": "2026-09-12T00:54:03.118622+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 426,
"listingErrors": 427,
"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": "2026-09-12T00:50:59.493726+00:00",
"updatedAt": "2026-09-12T00:54:03.095331+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T00:49:13.657369+00:00",
"generatedAt": "2026-09-12T00:52:08.235314+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": "2026-09-12T00:43:33.454278+00:00",
"lastSyncTime": "2026-09-12T00:43:33.238151+00:00",
"generatedAt": "2026-09-12T00:52:00.246547+00:00",
"lastSyncTime": "2026-09-12T00:52:00.210563+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1788,9 +1788,9 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 87,
"decisionFailureRate": 0.8878,
"decisionSuccessRate": 0.1122,
"decisionTotal": 98,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 99,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
@@ -1801,16 +1801,16 @@
"验证失败": 47
},
"failureCount": 156,
"failureRate": 0.9341,
"failureRate": 0.9286,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 11,
"successRate": 0.0659,
"successCount": 12,
"successRate": 0.0714,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 167,
"total": 168,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2312,9 +2312,9 @@
},
"unknown": {
"attributableFailureCount": 141,
"decisionFailureRate": 0.7382,
"decisionSuccessRate": 0.2618,
"decisionTotal": 191,
"decisionFailureRate": 0.7344,
"decisionSuccessRate": 0.2656,
"decisionTotal": 192,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
@@ -2327,13 +2327,13 @@
"验证失败": 673
},
"failureCount": 1004,
"failureRate": 0.9526,
"failureRate": 0.9517,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 50,
"successRate": 0.0474,
"total": 1054,
"successCount": 51,
"successRate": 0.0483,
"total": 1055,
"unresolvedFailureCount": 862
},
"vllm": {
@@ -2464,7 +2464,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T00:43:33.449427+00:00",
"generatedAt": "2026-09-12T00:52:00.242533+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2628,9 +2628,9 @@
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 88,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 99,
"decisionFailureRate": 0.88,
"decisionSuccessRate": 0.12,
"decisionTotal": 100,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
@@ -2641,13 +2641,13 @@
"验证失败": 47
},
"failureCount": 157,
"failureRate": 0.9345,
"failureRate": 0.929,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 11,
"successRate": 0.0655,
"total": 168,
"successCount": 12,
"successRate": 0.071,
"total": 169,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -4330,28 +4330,28 @@
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 1,
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2,
"model_load": 14,
"model_load": 13,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"failureCount": 18,
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T17:04:58.435558+00:00",
"lastTerminalAt": "2026-09-12T00:52:00.210542+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.05,
"successCount": 2,
"successRate": 0.1,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
@@ -4408,17 +4408,17 @@
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 5
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4430,7 +4430,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -7055,13 +7055,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1669,
"totalRecords": 1756,
"terminalRecords": 1670,
"totalRecords": 1757,
"totals": {
"attributableFailureCount": 442,
"decisionFailureRate": 0.8893,
"decisionSuccessRate": 0.1107,
"decisionTotal": 497,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 498,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 40,
@@ -7076,29 +7076,30 @@
"验证失败": 673
},
"failureCount": 1614,
"failureRate": 0.967,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 55,
"successRate": 0.033,
"total": 1669,
"successCount": 56,
"successRate": 0.0335,
"total": 1670,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 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。",
"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 MetaX_c-500 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|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 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7113,11 +7114,10 @@
"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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|unknown|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-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1756,
"summarizedRecords": 1757,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T00:52:00.210542+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T00:49:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523319", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207568+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079945", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207605+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079258", "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", "framework": "vllm", "lastSyncTime": "2026-09-11T21:18:30.415792+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T21:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080096", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T11:42:26.289451+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:35:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4007714", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T11:42:26.289433+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:25:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483789", "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": "2026-09-08T11:18:26.601995+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079157", "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": "2026-09-08T11:18:26.601968+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:53:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079200", "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