state: generation 6036 (cycle)

This commit is contained in:
2026-09-12 05:00:23 +00:00
parent 9cbb9271b6
commit 87cd6f4110
9 changed files with 2053 additions and 2053 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T04:41:36.495853+00:00",
"lastSyncTime": "2026-09-12T04:41:36.246914+00:00",
"generatedAt": "2026-09-12T04:58:37.438591+00:00",
"lastSyncTime": "2026-09-12T04:58:37.211400+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2286,19 +2286,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 37,
"attributableFailureCount": 39,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 28,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 53,
"failureCount": 55,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2308,7 +2308,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 53,
"total": 55,
"unresolvedFailureCount": 16
}
},
@@ -2377,30 +2377,30 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 252,
"decisionFailureRate": 0.9882,
"decisionSuccessRate": 0.0118,
"decisionTotal": 255,
"attributableFailureCount": 254,
"decisionFailureRate": 0.9883,
"decisionSuccessRate": 0.0117,
"decisionTotal": 257,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 174,
"memory_capacity": 6,
"model_load": 21,
"model_load": 22,
"platform_infrastructure": 1,
"repository_structure": 6,
"repository_structure": 7,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 472,
"failureCount": 474,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0063,
"total": 475,
"total": 477,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2505,7 +2505,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T04:41:36.489015+00:00",
"generatedAt": "2026-09-12T04:58:37.432031+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2811,28 +2811,28 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 40,
"attributableFailureCount": 42,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 40,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 31,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2,
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 94,
"failureCount": 96,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 94,
"total": 96,
"unresolvedFailureCount": 54
}
},
@@ -4777,23 +4777,24 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 3,
"repository_structure": 1,
"model_load": 1,
"repository_structure": 2,
"runtime_memory": 1
},
"failureCount": 17,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T21:18:30.415792+00:00",
"lastTerminalAt": "2026-09-12T04:58:37.211377+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4801,7 +4802,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 17,
"total": 19,
"unresolvedFailureCount": 12
}
},
@@ -7240,40 +7241,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1685,
"totalRecords": 1772,
"terminalRecords": 1687,
"totalRecords": 1774,
"totals": {
"attributableFailureCount": 457,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 513,
"attributableFailureCount": 459,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 515,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 41,
"framework_architecture_unsupported": 281,
"memory_capacity": 11,
"model_load": 65,
"model_load": 66,
"platform_infrastructure": 4,
"repository_structure": 6,
"repository_structure": 7,
"runtime_memory": 6,
"tokenizer_compatibility": 47,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1629,
"failureCount": 1631,
"failureRate": 0.9668,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0332,
"total": 1685,
"total": 1687,
"unresolvedFailureCount": 1168
},
"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。",
@@ -7282,7 +7284,6 @@
"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。",
@@ -7304,6 +7305,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1772,
"summarizedRecords": 1774,
"version": 1
}