state: generation 5116 (cycle)

This commit is contained in:
2026-09-10 10:23:07 +00:00
parent 86a86715dc
commit ec4d4ff16f
9 changed files with 2195 additions and 2196 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T10:12:25.956598+00:00",
"lastSyncTime": "2026-09-10T10:12:25.704447+00:00",
"generatedAt": "2026-09-10T10:21:30.246957+00:00",
"lastSyncTime": "2026-09-10T10:21:30.006897+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 49,
"failureCount": 50,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 49,
"unresolvedFailureCount": 14
"total": 50,
"unresolvedFailureCount": 15
}
},
"frameworkSummaries": {
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 158,
"ambiguous_runtime": 159,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 415,
"failureCount": 416,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 416,
"unresolvedFailureCount": 179
"total": 417,
"unresolvedFailureCount": 180
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T10:12:25.950299+00:00",
"generatedAt": "2026-09-10T10:21:30.242348+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2763,15 +2763,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 89,
"failureCount": 90,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 89,
"unresolvedFailureCount": 51
"total": 90,
"unresolvedFailureCount": 52
}
},
"observedGpuMemoryGiB": {
@@ -4531,17 +4531,16 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 1,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
@@ -4553,7 +4552,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|unknown|text-generation": {
@@ -4687,16 +4686,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T09:47:33.262404+00:00",
"lastTerminalAt": "2026-09-10T10:21:30.006897+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4704,8 +4703,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 11
"total": 20,
"unresolvedFailureCount": 12
}
},
"recentProfileCombinationStats": {
@@ -7055,15 +7054,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1554,
"totalRecords": 1641,
"terminalRecords": 1555,
"totalRecords": 1642,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 328,
"ambiguous_runtime": 329,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7075,21 +7074,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1503,
"failureCount": 1504,
"failureRate": 0.9672,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0328,
"total": 1554,
"unresolvedFailureCount": 1096
"total": 1555,
"unresolvedFailureCount": 1097
},
"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 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。",
"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。",
@@ -7097,7 +7096,7 @@
"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 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。",
"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。",
@@ -7118,6 +7117,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1641,
"summarizedRecords": 1642,
"version": 1
}