state: generation 11720 (cycle_no_slots)

This commit is contained in:
2026-09-21 20:34:37 +00:00
parent 8ecb07b7f5
commit c0450d1199
7 changed files with 2110 additions and 2090 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T20:32:52.267273+00:00",
"lastSyncTime": "2026-09-21T20:32:51.958999+00:00",
"generatedAt": "2026-09-21T20:34:21.873332+00:00",
"lastSyncTime": "2026-09-21T20:34:21.547032+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2977,24 +2977,24 @@
"decisionSuccessRate": 0.0625,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 36,
"ambiguous_runtime": 37,
"context_length": 3,
"framework_architecture_unsupported": 26,
"memory_capacity": 1,
"参数/模板问题": 8
},
"failureCount": 74,
"failureRate": 0.9737,
"failureCount": 75,
"failureRate": 0.974,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0263,
"successRate": 0.026,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 76,
"unresolvedFailureCount": 44
"total": 77,
"unresolvedFailureCount": 45
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 68,
@@ -3287,9 +3287,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 39
"ambiguous_runtime": 40
},
"failureCount": 39,
"failureCount": 40,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3299,8 +3299,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 39,
"unresolvedFailureCount": 39
"total": 40,
"unresolvedFailureCount": 40
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 44,
@@ -5632,7 +5632,7 @@
"decisionSuccessRate": 0.0391,
"decisionTotal": 128,
"failureBreakdown": {
"ambiguous_runtime": 198,
"ambiguous_runtime": 199,
"backend_operator": 8,
"framework_architecture_unsupported": 23,
"memory_capacity": 7,
@@ -5641,15 +5641,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 351,
"failureCount": 352,
"failureRate": 0.986,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.014,
"total": 356,
"unresolvedFailureCount": 211
"total": 357,
"unresolvedFailureCount": 212
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 77,
@@ -5657,7 +5657,7 @@
"decisionSuccessRate": 0.0253,
"decisionTotal": 79,
"failureBreakdown": {
"ambiguous_runtime": 85,
"ambiguous_runtime": 86,
"backend_operator": 1,
"context_length": 3,
"framework_architecture_unsupported": 66,
@@ -5668,18 +5668,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 27
},
"failureCount": 190,
"failureCount": 191,
"failureRate": 0.9896,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0104,
"total": 192,
"unresolvedFailureCount": 112
"total": 193,
"unresolvedFailureCount": 113
}
},
"generatedAt": "2026-09-21T20:32:52.255753+00:00",
"generatedAt": "2026-09-21T20:34:21.861695+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5687,7 +5687,7 @@
"decisionSuccessRate": 0.161,
"decisionTotal": 118,
"failureBreakdown": {
"ambiguous_runtime": 97,
"ambiguous_runtime": 98,
"context_length": 3,
"framework_architecture_unsupported": 91,
"memory_capacity": 2,
@@ -5697,15 +5697,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 265,
"failureRate": 0.9331,
"failureCount": 266,
"failureRate": 0.9333,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0669,
"total": 284,
"unresolvedFailureCount": 166
"successRate": 0.0667,
"total": 285,
"unresolvedFailureCount": 167
},
"Ascend_910-b4": {
"attributableFailureCount": 322,
@@ -5741,7 +5741,7 @@
"decisionSuccessRate": 0.1185,
"decisionTotal": 211,
"failureBreakdown": {
"ambiguous_runtime": 180,
"ambiguous_runtime": 181,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5755,15 +5755,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 671,
"failureCount": 672,
"failureRate": 0.9641,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0359,
"total": 696,
"unresolvedFailureCount": 483
"total": 697,
"unresolvedFailureCount": 484
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 717,
@@ -6325,10 +6325,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"context_length": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6340,8 +6340,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 4
"total": 6,
"unresolvedFailureCount": 5
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -8397,9 +8397,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "starcoder2",
@@ -8411,8 +8411,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 0,
@@ -17509,9 +17509,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -17523,8 +17523,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -17668,7 +17668,7 @@
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T18:20:35.656980+00:00",
"lastTerminalAt": "2026-09-21T20:34:21.547032+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -17758,19 +17758,18 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 1,
"ambiguous_runtime": 7,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 15,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
@@ -17782,8 +17781,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 12
"total": 13,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
@@ -18241,12 +18240,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T18:39:29.750872+00:00",
"lastTerminalAt": "2026-09-21T20:34:21.547005+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -18256,8 +18255,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -18766,12 +18765,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T18:20:35.656980+00:00",
"lastTerminalAt": "2026-09-21T20:34:21.547032+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -18781,8 +18780,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 0,
@@ -19095,9 +19094,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T19:49:37.657146+00:00",
@@ -19110,8 +19109,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": {
"attributableFailureCount": 0,
@@ -19138,31 +19137,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T17:22:47.256960+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -21751,6 +21725,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -24890,6 +24888,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|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": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -37980,15 +38002,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16405,
"totalRecords": 16599,
"terminalRecords": 16407,
"totalRecords": 16601,
"totals": {
"attributableFailureCount": 5918,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6864,
"failureBreakdown": {
"ambiguous_runtime": 4032,
"ambiguous_runtime": 4034,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
@@ -38004,31 +38026,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15459,
"failureCount": 15461,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0577,
"total": 16405,
"unresolvedFailureCount": 8616
"total": 16407,
"unresolvedFailureCount": 8618
},
"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。",
@@ -38068,6 +38090,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16599,
"summarizedRecords": 16601,
"version": 1
}