state: generation 4914 (cycle)

This commit is contained in:
2026-09-10 02:51:55 +00:00
parent e294460c01
commit b27ce1ff1b
9 changed files with 2027 additions and 2029 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T02:40:45.261552+00:00",
"lastSyncTime": "2026-09-10T02:40:44.943974+00:00",
"generatedAt": "2026-09-10T02:50:12.530651+00:00",
"lastSyncTime": "2026-09-10T02:50:12.317776+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1786,29 +1786,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.8701,
"decisionSuccessRate": 0.1299,
"decisionTotal": 77,
"attributableFailureCount": 68,
"decisionFailureRate": 0.8718,
"decisionSuccessRate": 0.1282,
"decisionTotal": 78,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 44,
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"model_load": 22,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 133,
"failureRate": 0.9301,
"failureCount": 134,
"failureRate": 0.9306,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0699,
"successRate": 0.0694,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 143,
"total": 144,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2224,14 +2224,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 42,
"failureCount": 43,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2241,8 +2241,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 42,
"unresolvedFailureCount": 7
"total": 43,
"unresolvedFailureCount": 8
}
},
"frameworkSummaries": {
@@ -2284,28 +2284,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 119,
"decisionFailureRate": 0.7126,
"decisionSuccessRate": 0.2874,
"decisionTotal": 167,
"attributableFailureCount": 120,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 168,
"failureBreakdown": {
"ambiguous_runtime": 101,
"backend_operator": 2,
"framework_architecture_unsupported": 85,
"framework_architecture_unsupported": 86,
"memory_capacity": 5,
"model_load": 24,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 949,
"failureCount": 950,
"failureRate": 0.9519,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0481,
"total": 997,
"total": 998,
"unresolvedFailureCount": 830
},
"vllm": {
@@ -2314,7 +2314,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 227,
"failureBreakdown": {
"ambiguous_runtime": 130,
"ambiguous_runtime": 131,
"backend_operator": 22,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
@@ -2325,15 +2325,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 379,
"failureCount": 380,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 379,
"unresolvedFailureCount": 151
"total": 380,
"unresolvedFailureCount": 152
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:40:45.256871+00:00",
"generatedAt": "2026-09-10T02:50:12.526687+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2599,26 +2599,26 @@
"unresolvedFailureCount": 41
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.8701,
"decisionSuccessRate": 0.1299,
"decisionTotal": 77,
"attributableFailureCount": 68,
"decisionFailureRate": 0.8718,
"decisionSuccessRate": 0.1282,
"decisionTotal": 78,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 44,
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"model_load": 22,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 133,
"failureRate": 0.9301,
"failureCount": 134,
"failureRate": 0.9306,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0699,
"total": 143,
"successRate": 0.0694,
"total": 144,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -2743,7 +2743,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2752,15 +2752,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 82,
"failureCount": 83,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 82,
"unresolvedFailureCount": 44
"total": 83,
"unresolvedFailureCount": 45
}
},
"observedGpuMemoryGiB": {
@@ -4199,7 +4199,7 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -4209,11 +4209,11 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -4224,11 +4224,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"backend_operator": 2,
"framework_architecture_unsupported": 2
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4240,26 +4240,26 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 6
"total": 9,
"unresolvedFailureCount": 5
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 8,
"model_load": 7
"framework_architecture_unsupported": 9,
"model_load": 6
},
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:40:44.943952+00:00",
"lastTerminalAt": "2026-09-10T02:50:12.317748+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4633,16 +4633,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T22:06:26.296264+00:00",
"lastTerminalAt": "2026-09-10T02:50:12.317776+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4650,8 +4650,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 17,
"unresolvedFailureCount": 7
}
},
"recentProfileCombinationStats": {
@@ -6764,17 +6764,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1488,
"totalRecords": 1572,
"terminalRecords": 1490,
"totalRecords": 1574,
"totals": {
"attributableFailureCount": 393,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 442,
"attributableFailureCount": 394,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 443,
"failureBreakdown": {
"ambiguous_runtime": 277,
"ambiguous_runtime": 278,
"backend_operator": 25,
"framework_architecture_unsupported": 268,
"framework_architecture_unsupported": 269,
"memory_capacity": 11,
"model_load": 46,
"platform_infrastructure": 2,
@@ -6784,21 +6784,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1439,
"failureCount": 1441,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0329,
"total": 1488,
"unresolvedFailureCount": 1044
"total": 1490,
"unresolvedFailureCount": 1045
},
"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。",
@@ -6806,7 +6806,7 @@
"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。",
@@ -6827,6 +6827,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1572,
"summarizedRecords": 1574,
"version": 1
}