state: generation 5037 (cycle)

This commit is contained in:
2026-09-10 07:06:53 +00:00
parent 5f3c51a6eb
commit 44b6cc3ba6
9 changed files with 2148 additions and 2149 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T06:56:24.262905+00:00",
"lastSyncTime": "2026-09-10T06:56:22.046035+00:00",
"generatedAt": "2026-09-10T07:04:57.589678+00:00",
"lastSyncTime": "2026-09-10T07:04:57.311825+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1551,24 +1551,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 77,
"failureRate": 0.9747,
"failureCount": 78,
"failureRate": 0.975,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0253,
"successRate": 0.025,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 79,
"unresolvedFailureCount": 57
"total": 80,
"unresolvedFailureCount": 58
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 46,
"failureCount": 48,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 46,
"unresolvedFailureCount": 11
"total": 48,
"unresolvedFailureCount": 13
}
},
"frameworkSummaries": {
@@ -2300,7 +2300,7 @@
"decisionSuccessRate": 0.284,
"decisionTotal": 169,
"failureBreakdown": {
"ambiguous_runtime": 106,
"ambiguous_runtime": 107,
"backend_operator": 2,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
@@ -2309,15 +2309,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 956,
"failureCount": 957,
"failureRate": 0.9522,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0478,
"total": 1004,
"unresolvedFailureCount": 835
"total": 1005,
"unresolvedFailureCount": 836
},
"vllm": {
"attributableFailureCount": 230,
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 148,
"ambiguous_runtime": 150,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 400,
"failureCount": 402,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 400,
"unresolvedFailureCount": 169
"total": 402,
"unresolvedFailureCount": 171
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T06:56:24.258540+00:00",
"generatedAt": "2026-09-10T07:04:57.585456+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2527,21 +2527,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 77,
"failureRate": 0.9747,
"failureCount": 78,
"failureRate": 0.975,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0253,
"total": 79,
"unresolvedFailureCount": 57
"successRate": 0.025,
"total": 80,
"unresolvedFailureCount": 58
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 15,
"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": 86,
"failureCount": 88,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 86,
"unresolvedFailureCount": 48
"total": 88,
"unresolvedFailureCount": 50
}
},
"observedGpuMemoryGiB": {
@@ -4051,28 +4051,28 @@
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 8,
"failureRate": 0.8,
"failureCount": 9,
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:56:22.046014+00:00",
"lastTerminalAt": "2026-09-10T07:04:57.311794+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.2,
"successCount": 1,
"successRate": 0.1,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 5
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -4518,23 +4518,23 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 2
},
"failureCount": 2,
"failureRate": 0.5,
"failureRate": 0.6667,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.5,
"successCount": 1,
"successRate": 0.3333,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 4,
"total": 3,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -4646,16 +4646,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 16,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:03:48.106939+00:00",
"lastTerminalAt": "2026-09-10T07:04:57.311815+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4663,8 +4663,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 8
"total": 18,
"unresolvedFailureCount": 10
}
},
"recentProfileCombinationStats": {
@@ -6897,15 +6897,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1523,
"totalRecords": 1610,
"terminalRecords": 1526,
"totalRecords": 1613,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 304,
"ambiguous_runtime": 307,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6917,21 +6917,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1474,
"failureRate": 0.9678,
"failureCount": 1477,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0322,
"total": 1523,
"unresolvedFailureCount": 1072
"successRate": 0.0321,
"total": 1526,
"unresolvedFailureCount": 1075
},
"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。",
@@ -6939,7 +6939,7 @@
"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。",
@@ -6960,6 +6960,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1610,
"summarizedRecords": 1613,
"version": 1
}