state: generation 5287 (cycle)

This commit is contained in:
2026-09-10 17:42:29 +00:00
parent ab1dd1282d
commit 3f0e822043
9 changed files with 2038 additions and 2040 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T17:30:55.555030+00:00",
"lastSyncTime": "2026-09-10T17:30:55.344638+00:00",
"generatedAt": "2026-09-10T17:40:38.619379+00:00",
"lastSyncTime": "2026-09-10T17:40:38.407692+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1545,24 +1545,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 87,
"failureRate": 0.9775,
"failureCount": 88,
"failureRate": 0.9778,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0225,
"successRate": 0.0222,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 89,
"unresolvedFailureCount": 67
"total": 90,
"unresolvedFailureCount": 68
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2296,7 +2296,7 @@
"decisionSuccessRate": 0.2759,
"decisionTotal": 174,
"failureBreakdown": {
"ambiguous_runtime": 122,
"ambiguous_runtime": 123,
"backend_operator": 4,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
@@ -2305,15 +2305,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 977,
"failureCount": 978,
"failureRate": 0.9532,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0468,
"total": 1025,
"unresolvedFailureCount": 851
"total": 1026,
"unresolvedFailureCount": 852
},
"vllm": {
"attributableFailureCount": 240,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T17:30:55.550874+00:00",
"generatedAt": "2026-09-10T17:40:38.613684+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2523,21 +2523,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 87,
"failureRate": 0.9775,
"failureCount": 88,
"failureRate": 0.9778,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0225,
"total": 89,
"unresolvedFailureCount": 67
"successRate": 0.0222,
"total": 90,
"unresolvedFailureCount": 68
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -4116,15 +4116,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T17:30:55.344638+00:00",
"lastTerminalAt": "2026-09-10T17:40:38.407692+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4132,8 +4132,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 15
"total": 18,
"unresolvedFailureCount": 16
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4169,11 +4169,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4185,8 +4185,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"total": 19,
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4637,9 +4637,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T15:41:33.599000+00:00",
@@ -4652,8 +4652,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
@@ -7169,15 +7169,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1614,
"totalRecords": 1701,
"terminalRecords": 1615,
"totalRecords": 1702,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"failureBreakdown": {
"ambiguous_runtime": 367,
"ambiguous_runtime": 368,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7189,31 +7189,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1562,
"failureCount": 1563,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0322,
"total": 1614,
"unresolvedFailureCount": 1138
"total": 1615,
"unresolvedFailureCount": 1139
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 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 Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"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。",
"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-x4|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 Mthreads_s4000|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7228,10 +7227,11 @@
"组合 hygon_k100-ai|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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1701,
"summarizedRecords": 1702,
"version": 1
}