state: generation 21879 (cycle)

This commit is contained in:
2026-10-07 14:48:02 +00:00
parent 6ea4d41125
commit 4c1b4ee84d
9 changed files with 1841 additions and 1795 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T14:31:58.421413+00:00",
"lastSyncTime": "2026-10-07T14:31:58.345576+00:00",
"generatedAt": "2026-10-07T14:46:46.668397+00:00",
"lastSyncTime": "2026-10-07T14:46:46.372736+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4448,10 +4448,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 165,
"ambiguous_runtime": 166,
"参数/模板问题": 3
},
"failureCount": 168,
"failureCount": 169,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4461,8 +4461,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 168,
"unresolvedFailureCount": 168
"total": 169,
"unresolvedFailureCount": 169
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5330,14 +5330,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 26,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 137,
"failureCount": 138,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5347,8 +5347,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 137,
"unresolvedFailureCount": 72
"total": 138,
"unresolvedFailureCount": 73
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 665,
@@ -5586,22 +5586,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 26,
"model_load": 15,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 24
},
"failureCount": 137,
"failureCount": 138,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 137,
"unresolvedFailureCount": 72
"total": 138,
"unresolvedFailureCount": 73
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 48,
@@ -5633,7 +5633,7 @@
"decisionSuccessRate": 0.0281,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 369,
"ambiguous_runtime": 370,
"backend_operator": 9,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
@@ -5642,15 +5642,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 580,
"failureCount": 581,
"failureRate": 0.9915,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0085,
"total": 585,
"unresolvedFailureCount": 382
"total": 586,
"unresolvedFailureCount": 383
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 155,
@@ -5681,7 +5681,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T14:31:58.404685+00:00",
"generatedAt": "2026-10-07T14:46:46.651700+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5913,7 +5913,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 254,
"ambiguous_runtime": 255,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -5926,15 +5926,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 425,
"failureCount": 426,
"failureRate": 0.9838,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0162,
"total": 432,
"unresolvedFailureCount": 325
"total": 433,
"unresolvedFailureCount": 326
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -6079,7 +6079,7 @@
"decisionSuccessRate": 0.0461,
"decisionTotal": 781,
"failureBreakdown": {
"ambiguous_runtime": 346,
"ambiguous_runtime": 347,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
@@ -6094,15 +6094,15 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1593,
"failureCount": 1594,
"failureRate": 0.9779,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0221,
"total": 1629,
"unresolvedFailureCount": 844
"total": 1630,
"unresolvedFailureCount": 845
}
},
"observedGpuMemoryGiB": {
@@ -18883,10 +18883,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"参数/模板问题": 1
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -18898,8 +18898,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 18
"total": 19,
"unresolvedFailureCount": 19
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none": {
"attributableFailureCount": 0,
@@ -23861,10 +23861,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"runtime_memory": 1
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "gemma2",
@@ -23876,8 +23876,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 3
"total": 5,
"unresolvedFailureCount": 4
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -25709,9 +25709,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 9
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25723,8 +25723,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 16,
@@ -26827,9 +26827,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-22T08:17:47.558862+00:00",
@@ -26842,8 +26842,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none": {
"attributableFailureCount": 0,
@@ -28128,12 +28128,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T14:24:51.661617+00:00",
"lastTerminalAt": "2026-10-07T14:46:46.372736+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -28143,8 +28143,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -48749,6 +48749,30 @@
"total": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 35,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -56261,6 +56285,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -58210,15 +58258,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17403,
"totalRecords": 17660,
"terminalRecords": 17405,
"totalRecords": 17662,
"totals": {
"attributableFailureCount": 6247,
"decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354,
"decisionTotal": 7225,
"failureBreakdown": {
"ambiguous_runtime": 4565,
"ambiguous_runtime": 4567,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -58234,15 +58282,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16425,
"failureCount": 16427,
"failureRate": 0.9438,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0562,
"total": 17403,
"unresolvedFailureCount": 9226
"total": 17405,
"unresolvedFailureCount": 9228
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -58251,14 +58299,14 @@
"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 Ascend_910-b3 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 Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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-x4 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 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。",
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -58303,6 +58351,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17660,
"summarizedRecords": 17662,
"version": 1
}