state: generation 4911 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T02:32:07.743588+00:00",
|
||||
"lastSyncTime": "2026-09-10T02:32:07.501704+00:00",
|
||||
"generatedAt": "2026-09-10T02:40:45.261552+00:00",
|
||||
"lastSyncTime": "2026-09-10T02:40:44.943974+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1540,24 +1540,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 75,
|
||||
"failureRate": 0.974,
|
||||
"failureCount": 76,
|
||||
"failureRate": 0.9744,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.026,
|
||||
"successRate": 0.0256,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 55
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -1786,29 +1786,29 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 65,
|
||||
"decisionFailureRate": 0.8784,
|
||||
"decisionSuccessRate": 0.1216,
|
||||
"decisionTotal": 74,
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.8701,
|
||||
"decisionSuccessRate": 0.1299,
|
||||
"decisionTotal": 77,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 43,
|
||||
"framework_architecture_unsupported": 44,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 21,
|
||||
"model_load": 22,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 131,
|
||||
"failureRate": 0.9357,
|
||||
"failureCount": 133,
|
||||
"failureRate": 0.9301,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 9,
|
||||
"successRate": 0.0643,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0699,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 140,
|
||||
"total": 143,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -2284,29 +2284,29 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 117,
|
||||
"decisionFailureRate": 0.7134,
|
||||
"decisionSuccessRate": 0.2866,
|
||||
"decisionTotal": 164,
|
||||
"attributableFailureCount": 119,
|
||||
"decisionFailureRate": 0.7126,
|
||||
"decisionSuccessRate": 0.2874,
|
||||
"decisionTotal": 167,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 100,
|
||||
"ambiguous_runtime": 101,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 84,
|
||||
"framework_architecture_unsupported": 85,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 23,
|
||||
"model_load": 24,
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 946,
|
||||
"failureRate": 0.9527,
|
||||
"failureCount": 949,
|
||||
"failureRate": 0.9519,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 47,
|
||||
"successRate": 0.0473,
|
||||
"total": 993,
|
||||
"unresolvedFailureCount": 829
|
||||
"successCount": 48,
|
||||
"successRate": 0.0481,
|
||||
"total": 997,
|
||||
"unresolvedFailureCount": 830
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 227,
|
||||
@@ -2436,7 +2436,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T02:32:07.739281+00:00",
|
||||
"generatedAt": "2026-09-10T02:40:45.256871+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2516,21 +2516,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 75,
|
||||
"failureRate": 0.974,
|
||||
"failureCount": 76,
|
||||
"failureRate": 0.9744,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.026,
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 55
|
||||
"successRate": 0.0256,
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -2599,26 +2599,26 @@
|
||||
"unresolvedFailureCount": 41
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 65,
|
||||
"decisionFailureRate": 0.8784,
|
||||
"decisionSuccessRate": 0.1216,
|
||||
"decisionTotal": 74,
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.8701,
|
||||
"decisionSuccessRate": 0.1299,
|
||||
"decisionTotal": 77,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 43,
|
||||
"framework_architecture_unsupported": 44,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 21,
|
||||
"model_load": 22,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 131,
|
||||
"failureRate": 0.9357,
|
||||
"failureCount": 133,
|
||||
"failureRate": 0.9301,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 9,
|
||||
"successRate": 0.0643,
|
||||
"total": 140,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0699,
|
||||
"total": 143,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -4044,24 +4044,24 @@
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureRate": 0.7778,
|
||||
"failureCount": 8,
|
||||
"failureRate": 0.8,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T02:32:07.501704+00:00",
|
||||
"lastTerminalAt": "2026-09-10T02:40:44.943974+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.2222,
|
||||
"successRate": 0.2,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -4217,19 +4217,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"runtime_memory": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4241,35 +4240,35 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 17,
|
||||
"decisionFailureRate": 0.8333,
|
||||
"decisionSuccessRate": 0.1667,
|
||||
"decisionTotal": 18,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 6
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 7
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9,
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.85,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T02:23:37.132500+00:00",
|
||||
"lastTerminalAt": "2026-09-10T02:40:44.943952+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.15,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 3
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -6765,19 +6764,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1484,
|
||||
"totalRecords": 1568,
|
||||
"terminalRecords": 1488,
|
||||
"totalRecords": 1572,
|
||||
"totals": {
|
||||
"attributableFailureCount": 391,
|
||||
"decisionFailureRate": 0.8907,
|
||||
"decisionSuccessRate": 0.1093,
|
||||
"decisionTotal": 439,
|
||||
"attributableFailureCount": 393,
|
||||
"decisionFailureRate": 0.8891,
|
||||
"decisionSuccessRate": 0.1109,
|
||||
"decisionTotal": 442,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 276,
|
||||
"ambiguous_runtime": 277,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 267,
|
||||
"framework_architecture_unsupported": 268,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 45,
|
||||
"model_load": 46,
|
||||
"platform_infrastructure": 2,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 5,
|
||||
@@ -6785,21 +6784,21 @@
|
||||
"参数/模板问题": 94,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1436,
|
||||
"failureRate": 0.9677,
|
||||
"failureCount": 1439,
|
||||
"failureRate": 0.9671,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0323,
|
||||
"total": 1484,
|
||||
"unresolvedFailureCount": 1043
|
||||
"successCount": 49,
|
||||
"successRate": 0.0329,
|
||||
"total": 1488,
|
||||
"unresolvedFailureCount": 1044
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Ascend_910-b3 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 Sunrise_pt-200-x1 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 Ascend_910-b4 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 MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -6807,7 +6806,7 @@
|
||||
"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 Mthreads_s4000 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 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-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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -6828,6 +6827,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1568,
|
||||
"summarizedRecords": 1572,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user