state: generation 11634 (cycle)

This commit is contained in:
2026-09-21 19:17:49 +00:00
parent 6836066c66
commit b089aedf38
10 changed files with 1744 additions and 1749 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:13:54.430477+00:00",
"lastSyncTime": "2026-09-21T19:13:53.564431+00:00",
"generatedAt": "2026-09-21T19:17:36.046225+00:00",
"lastSyncTime": "2026-09-21T19:17:35.577982+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3102,7 +3102,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 106,
"ambiguous_runtime": 108,
"context_length": 1,
"framework_architecture_unsupported": 155,
"memory_capacity": 10,
@@ -3110,7 +3110,7 @@
"repository_structure": 27,
"tokenizer_compatibility": 11
},
"failureCount": 311,
"failureCount": 313,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3120,8 +3120,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 311,
"unresolvedFailureCount": 106
"total": 313,
"unresolvedFailureCount": 108
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -3474,9 +3474,9 @@
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"参数/模板问题": 11
"参数/模板问题": 12
},
"failureCount": 48,
"failureCount": 49,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3486,8 +3486,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 48,
"unresolvedFailureCount": 29
"total": 49,
"unresolvedFailureCount": 30
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -5426,7 +5426,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3629,
"failureBreakdown": {
"ambiguous_runtime": 1493,
"ambiguous_runtime": 1495,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5438,17 +5438,17 @@
"repository_structure": 470,
"runtime_memory": 64,
"tokenizer_compatibility": 412,
"参数/模板问题": 45
"参数/模板问题": 46
},
"failureCount": 5944,
"failureCount": 5947,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6032,
"unresolvedFailureCount": 1538
"total": 6035,
"unresolvedFailureCount": 1541
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5594,7 +5594,7 @@
"unresolvedFailureCount": 104
}
},
"generatedAt": "2026-09-21T19:13:54.417493+00:00",
"generatedAt": "2026-09-21T19:17:36.034836+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5628,7 +5628,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 175,
"ambiguous_runtime": 177,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5640,15 +5640,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 956,
"failureRate": 0.9382,
"failureCount": 958,
"failureRate": 0.9383,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0618,
"total": 1019,
"unresolvedFailureCount": 632
"successRate": 0.0617,
"total": 1021,
"unresolvedFailureCount": 634
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -5720,18 +5720,18 @@
"memory_capacity": 4,
"model_load": 3,
"tokenizer_compatibility": 2,
"参数/模板问题": 33,
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 209,
"failureRate": 0.9372,
"failureCount": 210,
"failureRate": 0.9375,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0628,
"total": 223,
"unresolvedFailureCount": 159
"successRate": 0.0625,
"total": 224,
"unresolvedFailureCount": 160
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -7760,9 +7760,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma2",
@@ -7774,8 +7774,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -7783,9 +7783,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7797,8 +7797,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -17246,9 +17246,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -17260,8 +17260,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 5,
@@ -17454,9 +17454,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 5,
"memory_capacity": 1
"memory_capacity": 1,
"参数/模板问题": 1
},
"failureCount": 20,
"failureRate": 1.0,
@@ -17975,12 +17976,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T19:13:53.564431+00:00",
"lastTerminalAt": "2026-09-21T19:17:35.577982+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -17990,8 +17991,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -20675,31 +20676,6 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T12:01:00.670660+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -20726,31 +20702,6 @@
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T12:01:00.670747+00:00",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -23884,6 +23835,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -23932,6 +23907,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -37356,15 +37355,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16370,
"totalRecords": 16564,
"terminalRecords": 16373,
"totalRecords": 16567,
"totals": {
"attributableFailureCount": 5908,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6854,
"failureBreakdown": {
"ambiguous_runtime": 4008,
"ambiguous_runtime": 4010,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
@@ -37376,35 +37375,35 @@
"repository_structure": 739,
"runtime_memory": 85,
"tokenizer_compatibility": 662,
"参数/模板问题": 3190,
"参数/模板问题": 3191,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15424,
"failureCount": 15427,
"failureRate": 0.9422,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0578,
"total": 16370,
"unresolvedFailureCount": 8591
"total": 16373,
"unresolvedFailureCount": 8594
},
"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 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 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。",
@@ -37444,6 +37443,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16564,
"summarizedRecords": 16567,
"version": 1
}