state: generation 6374 (cycle)

This commit is contained in:
2026-09-12 21:32:20 +00:00
parent 4292806846
commit 8623c45bcc
9 changed files with 2556 additions and 2624 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T20:49:10.669850+00:00",
"lastSyncTime": "2026-09-12T20:49:10.452723+00:00",
"generatedAt": "2026-09-12T21:28:41.538560+00:00",
"lastSyncTime": "2026-09-12T21:28:41.303490+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1911,30 +1911,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 90,
"decisionFailureRate": 0.8738,
"decisionSuccessRate": 0.1262,
"decisionTotal": 103,
"attributableFailureCount": 91,
"decisionFailureRate": 0.8667,
"decisionSuccessRate": 0.1333,
"decisionTotal": 105,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 40,
"model_load": 41,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 160,
"failureRate": 0.9249,
"failureCount": 161,
"failureRate": 0.92,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.0751,
"successCount": 14,
"successRate": 0.08,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 173,
"total": 175,
"unresolvedFailureCount": 69
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2437,29 +2437,29 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 147,
"decisionFailureRate": 0.7387,
"decisionSuccessRate": 0.2613,
"decisionTotal": 199,
"attributableFailureCount": 148,
"decisionFailureRate": 0.7363,
"decisionSuccessRate": 0.2637,
"decisionTotal": 201,
"failureBreakdown": {
"ambiguous_runtime": 136,
"backend_operator": 4,
"framework_architecture_unsupported": 93,
"memory_capacity": 5,
"model_load": 42,
"model_load": 43,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1016,
"failureRate": 0.9513,
"failureCount": 1017,
"failureRate": 0.9505,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 52,
"successRate": 0.0487,
"total": 1068,
"successCount": 53,
"successRate": 0.0495,
"total": 1070,
"unresolvedFailureCount": 868
},
"vllm": {
@@ -2591,7 +2591,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T20:49:10.666114+00:00",
"generatedAt": "2026-09-12T21:28:41.534086+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2755,27 +2755,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 91,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 104,
"attributableFailureCount": 92,
"decisionFailureRate": 0.8679,
"decisionSuccessRate": 0.1321,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 41,
"model_load": 42,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 161,
"failureRate": 0.9253,
"failureCount": 162,
"failureRate": 0.9205,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.0747,
"total": 174,
"successCount": 14,
"successRate": 0.0795,
"total": 176,
"unresolvedFailureCount": 69
},
"Kunlunxin_p-800": {
@@ -4602,30 +4602,30 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 14,
"consecutiveFailures": 2,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8235,
"decisionSuccessRate": 0.1765,
"decisionTotal": 17,
"decisionFailureRate": 0.7778,
"decisionSuccessRate": 0.2222,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 1,
"model_load": 13
},
"failureCount": 17,
"failureRate": 0.85,
"failureCount": 16,
"failureRate": 0.8,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T09:54:24.312986+00:00",
"lastTerminalAt": "2026-09-12T21:28:41.303467+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.15,
"successCount": 4,
"successRate": 0.2,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 3
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4660,9 +4660,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 6
},
"failureCount": 8,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4674,8 +4674,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 6,
"unresolvedFailureCount": 6
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4966,31 +4966,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T11:30:49.443166+00:00",
"modelType": "phi3small",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -5066,31 +5041,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T16:50:57.939999+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|zaya|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -7346,19 +7296,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1737,
"totalRecords": 1824,
"terminalRecords": 1739,
"totalRecords": 1826,
"totals": {
"attributableFailureCount": 495,
"decisionFailureRate": 0.8967,
"decisionSuccessRate": 0.1033,
"decisionTotal": 552,
"attributableFailureCount": 496,
"decisionFailureRate": 0.8953,
"decisionSuccessRate": 0.1047,
"decisionTotal": 554,
"failureBreakdown": {
"ambiguous_runtime": 407,
"backend_operator": 42,
"framework_architecture_unsupported": 308,
"memory_capacity": 11,
"model_load": 72,
"model_load": 73,
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
@@ -7366,20 +7316,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1680,
"failureRate": 0.9672,
"failureCount": 1681,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0328,
"total": 1737,
"successCount": 58,
"successRate": 0.0334,
"total": 1739,
"unresolvedFailureCount": 1181
},
"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。",
@@ -7388,7 +7339,6 @@
"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。",
@@ -7411,6 +7361,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1824,
"summarizedRecords": 1826,
"version": 1
}