state: generation 5096 (cycle)

This commit is contained in:
2026-09-10 09:32:05 +00:00
parent 13f889cb2e
commit 5c10f11bf7
9 changed files with 2129 additions and 2127 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T09:20:50.642259+00:00",
"lastSyncTime": "2026-09-10T09:20:50.207436+00:00",
"generatedAt": "2026-09-10T09:29:58.731302+00:00",
"lastSyncTime": "2026-09-10T09:29:56.132283+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2001,20 +2001,20 @@
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 31,
"attributableFailureCount": 32,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 31,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 3,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2024,7 +2024,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 26
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -2320,13 +2320,13 @@
"unresolvedFailureCount": 844
},
"vllm": {
"attributableFailureCount": 234,
"decisionFailureRate": 0.9957,
"decisionSuccessRate": 0.0043,
"decisionTotal": 235,
"attributableFailureCount": 235,
"decisionFailureRate": 0.9958,
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 155,
"backend_operator": 28,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
"model_load": 18,
@@ -2336,14 +2336,14 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 411,
"failureCount": 412,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 412,
"total": 413,
"unresolvedFailureCount": 176
},
"vllm-mlu": {
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T09:20:50.635463+00:00",
"generatedAt": "2026-09-10T09:29:58.725727+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2678,13 +2678,13 @@
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
"attributableFailureCount": 32,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionTotal": 34,
"attributableFailureCount": 33,
"decisionFailureRate": 0.9429,
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 3,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
"model_load": 3,
@@ -2693,14 +2693,14 @@
"参数/模板问题": 7,
"验证失败": 26
},
"failureCount": 91,
"failureRate": 0.9785,
"failureCount": 92,
"failureRate": 0.9787,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0215,
"total": 93,
"successRate": 0.0213,
"total": 94,
"unresolvedFailureCount": 59
},
"Sunrise_pt-200-x1": {
@@ -4257,11 +4257,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 4,
"backend_operator": 2,
"framework_architecture_unsupported": 2
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4273,8 +4273,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 5
"total": 8,
"unresolvedFailureCount": 4
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
@@ -4429,24 +4429,24 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T08:45:45.454624+00:00",
"lastTerminalAt": "2026-09-10T09:29:56.132283+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4454,7 +4454,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 12,
"total": 13,
"unresolvedFailureCount": 7
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -6986,16 +6986,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1549,
"totalRecords": 1636,
"terminalRecords": 1550,
"totalRecords": 1637,
"totals": {
"attributableFailureCount": 404,
"decisionFailureRate": 0.8879,
"decisionSuccessRate": 0.1121,
"decisionTotal": 455,
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 324,
"backend_operator": 33,
"backend_operator": 34,
"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": 1498,
"failureCount": 1499,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0329,
"total": 1549,
"total": 1550,
"unresolvedFailureCount": 1092
},
"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。",
@@ -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 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。",
@@ -7049,6 +7049,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1636,
"summarizedRecords": 1637,
"version": 1
}