state: generation 11833 (cycle_no_slots)

This commit is contained in:
2026-09-21 22:25:24 +00:00
parent c509b8378a
commit 0e945a9887
6 changed files with 2021 additions and 2022 deletions

View File

@@ -2848,7 +2848,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T22:23:42.125073+00:00",
"generatedAt": "2026-09-21T22:25:09.209335+00:00",
"summary": {
"activeBlockCount": 143,
"byGpuFramework": {

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T22:22:17.821193+00:00",
"lastSyncTime": "2026-09-21T22:22:17.565358+00:00",
"generatedAt": "2026-09-21T22:25:09.094897+00:00",
"lastSyncTime": "2026-09-21T22:25:08.760152+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3306,23 +3306,23 @@
"decisionSuccessRate": 0.2542,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 31,
"model_load": 11,
"tokenizer_compatibility": 2
},
"failureCount": 55,
"failureRate": 0.7857,
"failureCount": 56,
"failureRate": 0.7887,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2143,
"successRate": 0.2113,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 70,
"unresolvedFailureCount": 11
"total": 71,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -5509,7 +5509,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3634,
"failureBreakdown": {
"ambiguous_runtime": 1498,
"ambiguous_runtime": 1499,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5523,15 +5523,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5955,
"failureCount": 5956,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6043,
"unresolvedFailureCount": 1544
"total": 6044,
"unresolvedFailureCount": 1545
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5677,7 +5677,7 @@
"unresolvedFailureCount": 120
}
},
"generatedAt": "2026-09-21T22:22:17.810626+00:00",
"generatedAt": "2026-09-21T22:25:09.082653+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5739,7 +5739,7 @@
"decisionSuccessRate": 0.1185,
"decisionTotal": 211,
"failureBreakdown": {
"ambiguous_runtime": 189,
"ambiguous_runtime": 190,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5753,15 +5753,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 680,
"failureRate": 0.9645,
"failureCount": 681,
"failureRate": 0.9646,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0355,
"total": 705,
"unresolvedFailureCount": 492
"successRate": 0.0354,
"total": 706,
"unresolvedFailureCount": 493
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 717,
@@ -8531,9 +8531,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "cohere2",
@@ -8545,8 +8545,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -25287,9 +25287,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -25302,8 +25302,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0,
@@ -38463,15 +38463,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16428,
"totalRecords": 16622,
"terminalRecords": 16429,
"totalRecords": 16623,
"totals": {
"attributableFailureCount": 5921,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6870,
"failureBreakdown": {
"ambiguous_runtime": 4048,
"ambiguous_runtime": 4049,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38487,31 +38487,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15479,
"failureCount": 15480,
"failureRate": 0.9422,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0578,
"total": 16428,
"unresolvedFailureCount": 8633
"total": 16429,
"unresolvedFailureCount": 8634
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-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-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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|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|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -38551,6 +38551,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16622,
"summarizedRecords": 16623,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff