state: generation 4958 (cycle)

This commit is contained in:
2026-09-10 04:56:16 +00:00
parent 6b0ea4aa55
commit aea334157d
9 changed files with 2969 additions and 2858 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T04:45:49.713641+00:00",
"lastSyncTime": "2026-09-10T04:45:49.293213+00:00",
"generatedAt": "2026-09-10T04:54:16.505309+00:00",
"lastSyncTime": "2026-09-10T04:54:16.213468+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1398,12 +1398,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 42,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1413,8 +1413,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 42,
"unresolvedFailureCount": 16
"total": 44,
"unresolvedFailureCount": 18
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -2243,14 +2243,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2260,8 +2260,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 44,
"unresolvedFailureCount": 9
"total": 45,
"unresolvedFailureCount": 10
}
},
"frameworkSummaries": {
@@ -2333,7 +2333,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 135,
"ambiguous_runtime": 138,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2344,15 +2344,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 387,
"failureCount": 390,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 387,
"unresolvedFailureCount": 156
"total": 390,
"unresolvedFailureCount": 159
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2455,7 +2455,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T04:45:49.709300+00:00",
"generatedAt": "2026-09-10T04:54:16.501434+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2463,22 +2463,22 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 77,
"failureRate": 0.9872,
"failureCount": 79,
"failureRate": 0.9875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0128,
"total": 78,
"unresolvedFailureCount": 51
"successRate": 0.0125,
"total": 80,
"unresolvedFailureCount": 53
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
@@ -2762,7 +2762,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2771,15 +2771,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 84,
"failureCount": 85,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 84,
"unresolvedFailureCount": 46
"total": 85,
"unresolvedFailureCount": 47
}
},
"observedGpuMemoryGiB": {
@@ -3950,29 +3950,6 @@
}
},
"recentCombinationStats": {
"Ascend_910-b3|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T10:17:44.109335+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
@@ -3981,14 +3958,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 3
},
"failureCount": 13,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:32:07.501688+00:00",
"lastTerminalAt": "2026-09-10T04:54:16.213455+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3996,8 +3973,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 10
"total": 15,
"unresolvedFailureCount": 12
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4109,27 +4086,27 @@
"attributableFailureCount": 3,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 13,
"failureRate": 0.8667,
"failureRate": 0.9286,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T01:59:31.241099+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1333,
"successCount": 1,
"successRate": 0.0714,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 15,
"total": 14,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -4678,16 +4655,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:45:49.293187+00:00",
"lastTerminalAt": "2026-09-10T04:54:16.213427+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4695,8 +4672,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 7
"total": 18,
"unresolvedFailureCount": 8
}
},
"recentProfileCombinationStats": {
@@ -6905,15 +6882,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1502,
"totalRecords": 1589,
"terminalRecords": 1505,
"totalRecords": 1592,
"totals": {
"attributableFailureCount": 399,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 448,
"failureBreakdown": {
"ambiguous_runtime": 284,
"ambiguous_runtime": 287,
"backend_operator": 29,
"framework_architecture_unsupported": 270,
"memory_capacity": 11,
@@ -6925,21 +6902,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1453,
"failureCount": 1456,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0326,
"total": 1502,
"unresolvedFailureCount": 1052
"total": 1505,
"unresolvedFailureCount": 1055
},
"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。",
@@ -6947,7 +6924,7 @@
"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。",
@@ -6968,6 +6945,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1589,
"summarizedRecords": 1592,
"version": 1
}