state: generation 8635 (cycle)

This commit is contained in:
2026-09-17 08:37:17 +00:00
parent 82962531cb
commit d1daeac920
9 changed files with 1999 additions and 1953 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T08:17:06.050407+00:00",
"lastSyncTime": "2026-09-17T08:17:01.421000+00:00",
"generatedAt": "2026-09-17T08:34:57.406246+00:00",
"lastSyncTime": "2026-09-17T08:34:57.207631+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2375,10 +2375,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 58,
"参数/模板问题": 2
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2388,8 +2388,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 59,
"unresolvedFailureCount": 59
"total": 60,
"unresolvedFailureCount": 60
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2933,7 +2933,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 62,
"ambiguous_runtime": 63,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 1,
@@ -2941,15 +2941,15 @@
"tokenizer_compatibility": 45,
"参数/模板问题": 8
},
"failureCount": 134,
"failureCount": 135,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 0,
"successRate": 0.0,
"total": 134,
"unresolvedFailureCount": 70
"total": 135,
"unresolvedFailureCount": 71
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 9,
@@ -2971,7 +2971,7 @@
"unresolvedFailureCount": 7
}
},
"generatedAt": "2026-09-17T08:17:06.044964+00:00",
"generatedAt": "2026-09-17T08:34:57.400621+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 54,
@@ -3168,20 +3168,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 104,
"ambiguous_runtime": 105,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 130,
"failureCount": 131,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 130,
"unresolvedFailureCount": 129
"total": 131,
"unresolvedFailureCount": 130
},
"MetaX_c-500": {
"attributableFailureCount": 60,
@@ -5458,6 +5458,29 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -10525,6 +10548,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -12269,15 +12316,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2108,
"totalRecords": 2211,
"terminalRecords": 2109,
"totalRecords": 2212,
"totals": {
"attributableFailureCount": 686,
"decisionFailureRate": 0.884,
"decisionSuccessRate": 0.116,
"decisionTotal": 776,
"failureBreakdown": {
"ambiguous_runtime": 516,
"ambiguous_runtime": 517,
"backend_operator": 47,
"framework_architecture_unsupported": 456,
"memory_capacity": 12,
@@ -12289,28 +12336,28 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2018,
"failureCount": 2019,
"failureRate": 0.9573,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 90,
"successRate": 0.0427,
"total": 2108,
"unresolvedFailureCount": 1322
"total": 2109,
"unresolvedFailureCount": 1323
},
"warnings": [
"GPU Mthreads_s4000 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 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 Biren_166m 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 hygon_k100-ai 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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。",
"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。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -12336,6 +12383,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2211,
"summarizedRecords": 2212,
"version": 1
}