state: generation 5081 (cycle)

This commit is contained in:
2026-09-10 08:47:38 +00:00
parent 08be1fde6c
commit 32ed846e9e
11 changed files with 1907 additions and 1909 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T08:28:01.488214+00:00",
"lastSyncTime": "2026-09-10T08:28:01.218249+00:00",
"generatedAt": "2026-09-10T08:45:45.905614+00:00",
"lastSyncTime": "2026-09-10T08:45:45.454674+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2001,20 +2001,20 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 30,
"attributableFailureCount": 31,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 30,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 24,
"backend_operator": 2,
"ambiguous_runtime": 26,
"backend_operator": 3,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 54,
"failureCount": 57,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2024,8 +2024,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 54,
"unresolvedFailureCount": 24
"total": 57,
"unresolvedFailureCount": 26
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2320,13 +2320,13 @@
"unresolvedFailureCount": 842
},
"vllm": {
"attributableFailureCount": 232,
"attributableFailureCount": 233,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 233,
"decisionTotal": 234,
"failureBreakdown": {
"ambiguous_runtime": 151,
"backend_operator": 26,
"ambiguous_runtime": 153,
"backend_operator": 27,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 405,
"failureRate": 0.9975,
"failureCount": 408,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0025,
"total": 406,
"unresolvedFailureCount": 172
"successRate": 0.0024,
"total": 409,
"unresolvedFailureCount": 174
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T08:28:01.484104+00:00",
"generatedAt": "2026-09-10T08:45:45.900554+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2678,13 +2678,13 @@
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.9394,
"decisionSuccessRate": 0.0606,
"decisionTotal": 33,
"attributableFailureCount": 32,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 24,
"backend_operator": 2,
"ambiguous_runtime": 26,
"backend_operator": 3,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 3,
@@ -2693,15 +2693,15 @@
"参数/模板问题": 7,
"验证失败": 26
},
"failureCount": 88,
"failureRate": 0.9778,
"failureCount": 91,
"failureRate": 0.9785,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0222,
"total": 90,
"unresolvedFailureCount": 57
"successRate": 0.0215,
"total": 93,
"unresolvedFailureCount": 59
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 30,
@@ -4041,20 +4041,20 @@
"unresolvedFailureCount": 13
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
"attributableFailureCount": 7,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 9,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 8,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 4,
"model_load": 1
},
"failureCount": 16,
"failureRate": 0.9412,
"failureCount": 15,
"failureRate": 0.9375,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:11:26.144205+00:00",
@@ -4062,10 +4062,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0588,
"successRate": 0.0625,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"total": 16,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4429,24 +4429,24 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 1,
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 9,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T08:28:01.218218+00:00",
"lastTerminalAt": "2026-09-10T08:45:45.454624+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4454,8 +4454,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 5
"total": 12,
"unresolvedFailureCount": 7
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6986,16 +6986,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1541,
"totalRecords": 1628,
"terminalRecords": 1544,
"totalRecords": 1631,
"totals": {
"attributableFailureCount": 402,
"decisionFailureRate": 0.8874,
"decisionSuccessRate": 0.1126,
"decisionTotal": 453,
"attributableFailureCount": 403,
"decisionFailureRate": 0.8877,
"decisionSuccessRate": 0.1123,
"decisionTotal": 454,
"failureBreakdown": {
"ambiguous_runtime": 318,
"backend_operator": 31,
"ambiguous_runtime": 320,
"backend_operator": 32,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
@@ -7006,21 +7006,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1490,
"failureRate": 0.9669,
"failureCount": 1493,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0331,
"total": 1541,
"unresolvedFailureCount": 1086
"successRate": 0.033,
"total": 1544,
"unresolvedFailureCount": 1088
},
"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。",
@@ -7028,7 +7028,7 @@
"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。",
@@ -7049,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1628,
"summarizedRecords": 1631,
"version": 1
}