state: generation 11734 (cycle_no_slots)

This commit is contained in:
2026-09-21 20:41:56 +00:00
parent bc26a389a7
commit 14f8bfb1f8
6 changed files with 1663 additions and 1621 deletions

View File

@@ -2850,7 +2850,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T20:39:58.157272+00:00",
"generatedAt": "2026-09-21T20:41:43.700052+00:00",
"summary": {
"activeBlockCount": 143,
"byGpuFramework": {

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T20:38:25.463942+00:00",
"lastSyncTime": "2026-09-21T20:38:25.158922+00:00",
"generatedAt": "2026-09-21T20:41:43.625847+00:00",
"lastSyncTime": "2026-09-21T20:41:43.555774+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4504,9 +4504,9 @@
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 17,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
@@ -4515,16 +4515,16 @@
"参数/模板问题": 13
},
"failureCount": 31,
"failureRate": 1.0,
"failureRate": 0.9688,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.0312,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 31,
"total": 32,
"unresolvedFailureCount": 14
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -5653,9 +5653,9 @@
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 77,
"decisionFailureRate": 0.9747,
"decisionSuccessRate": 0.0253,
"decisionTotal": 79,
"decisionFailureRate": 0.9625,
"decisionSuccessRate": 0.0375,
"decisionTotal": 80,
"failureBreakdown": {
"ambiguous_runtime": 88,
"backend_operator": 1,
@@ -5669,17 +5669,17 @@
"参数/模板问题": 27
},
"failureCount": 193,
"failureRate": 0.9897,
"failureRate": 0.9847,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0103,
"total": 195,
"successCount": 3,
"successRate": 0.0153,
"total": 196,
"unresolvedFailureCount": 115
}
},
"generatedAt": "2026-09-21T20:38:25.451761+00:00",
"generatedAt": "2026-09-21T20:41:43.615367+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5905,9 +5905,9 @@
},
"Kunlunxin_p-800": {
"attributableFailureCount": 19,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 19,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 188,
"backend_operator": 1,
@@ -5919,13 +5919,13 @@
"验证失败": 23
},
"failureCount": 251,
"failureRate": 1.0,
"failureRate": 0.996,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 251,
"successCount": 1,
"successRate": 0.004,
"total": 252,
"unresolvedFailureCount": 232
},
"Kunlunxin_r-200-8f": {
@@ -14815,6 +14815,27 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -34171,6 +34192,28 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -38073,13 +38116,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16409,
"totalRecords": 16603,
"terminalRecords": 16410,
"totalRecords": 16604,
"totals": {
"attributableFailureCount": 5918,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6864,
"decisionFailureRate": 0.8621,
"decisionSuccessRate": 0.1379,
"decisionTotal": 6865,
"failureBreakdown": {
"ambiguous_runtime": 4036,
"architecture_compatibility": 212,
@@ -38102,26 +38145,26 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successCount": 947,
"successRate": 0.0577,
"total": 16409,
"total": 16410,
"unresolvedFailureCount": 8620
},
"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。",
@@ -38161,6 +38204,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16603,
"summarizedRecords": 16604,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff