state: generation 5272 (cycle)

This commit is contained in:
2026-09-10 16:56:17 +00:00
parent a339232da1
commit 80d1dde7f5
9 changed files with 1957 additions and 1957 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T16:44:51.166987+00:00",
"lastSyncTime": "2026-09-10T16:44:50.902809+00:00",
"generatedAt": "2026-09-10T16:54:17.522980+00:00",
"lastSyncTime": "2026-09-10T16:54:17.206935+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1545,24 +1545,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 82,
"failureRate": 0.9762,
"failureCount": 83,
"failureRate": 0.9765,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0238,
"successRate": 0.0235,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 84,
"unresolvedFailureCount": 62
"total": 85,
"unresolvedFailureCount": 63
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2000,7 +2000,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2009,7 +2009,7 @@
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 62,
"failureCount": 63,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2019,8 +2019,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 62,
"unresolvedFailureCount": 30
"total": 63,
"unresolvedFailureCount": 31
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2296,7 +2296,7 @@
"decisionSuccessRate": 0.2759,
"decisionTotal": 174,
"failureBreakdown": {
"ambiguous_runtime": 117,
"ambiguous_runtime": 118,
"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": 972,
"failureRate": 0.9529,
"failureCount": 973,
"failureRate": 0.953,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0471,
"total": 1020,
"unresolvedFailureCount": 846
"successRate": 0.047,
"total": 1021,
"unresolvedFailureCount": 847
},
"vllm": {
"attributableFailureCount": 240,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 177,
"ambiguous_runtime": 178,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 442,
"failureCount": 443,
"failureRate": 0.9955,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0045,
"total": 444,
"unresolvedFailureCount": 201
"total": 445,
"unresolvedFailureCount": 202
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T16:44:51.162108+00:00",
"generatedAt": "2026-09-10T16:54:17.517562+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2523,21 +2523,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 82,
"failureRate": 0.9762,
"failureCount": 83,
"failureRate": 0.9765,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0238,
"total": 84,
"unresolvedFailureCount": 62
"successRate": 0.0235,
"total": 85,
"unresolvedFailureCount": 63
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -2679,7 +2679,7 @@
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2689,15 +2689,15 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 96,
"failureRate": 0.9796,
"failureCount": 97,
"failureRate": 0.9798,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0204,
"total": 98,
"unresolvedFailureCount": 63
"successRate": 0.0202,
"total": 99,
"unresolvedFailureCount": 64
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 36,
@@ -4116,15 +4116,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:30:05.632388+00:00",
"lastTerminalAt": "2026-09-10T16:54:17.206907+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": 12,
"unresolvedFailureCount": 10
"total": 13,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4426,16 +4426,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"runtime_memory": 1
},
"failureCount": 12,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T10:57:49.001753+00:00",
"lastTerminalAt": "2026-09-10T16:54:17.206935+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4443,8 +4443,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 7
"total": 13,
"unresolvedFailureCount": 8
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -7193,15 +7193,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1608,
"totalRecords": 1695,
"terminalRecords": 1610,
"totalRecords": 1697,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"failureBreakdown": {
"ambiguous_runtime": 361,
"ambiguous_runtime": 363,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7213,30 +7213,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1556,
"failureCount": 1558,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0323,
"total": 1608,
"unresolvedFailureCount": 1132
"total": 1610,
"unresolvedFailureCount": 1134
},
"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 Iluvatar_bi-150 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 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 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。",
"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。",
@@ -7251,11 +7252,10 @@
"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": 1695,
"summarizedRecords": 1697,
"version": 1
}