state: generation 20744 (cycle)

This commit is contained in:
2026-10-05 04:56:09 +00:00
parent 808350524b
commit ed6c2219d0
8 changed files with 1326 additions and 1257 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-05T04:45:06.244348+00:00",
"lastSyncTime": "2026-10-05T04:45:05.950071+00:00",
"generatedAt": "2026-10-05T04:54:31.130812+00:00",
"lastSyncTime": "2026-10-05T04:54:30.871106+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3640,25 +3640,25 @@
"decisionSuccessRate": 0.2647,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 47,
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 21,
"model_load": 4,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 77,
"failureRate": 0.8953,
"failureCount": 78,
"failureRate": 0.8966,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.1047,
"successRate": 0.1034,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 86,
"unresolvedFailureCount": 51
"total": 87,
"unresolvedFailureCount": 52
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 25,
@@ -5581,14 +5581,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 24,
"model_load": 13,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 118,
"failureCount": 119,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -5598,8 +5598,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 118,
"unresolvedFailureCount": 57
"total": 119,
"unresolvedFailureCount": 58
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 665,
@@ -5813,7 +5813,7 @@
"decisionSuccessRate": 0.3385,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 100,
"ambiguous_runtime": 101,
"framework_architecture_unsupported": 35,
"model_load": 7,
"platform_infrastructure": 1,
@@ -5821,15 +5821,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 151,
"failureRate": 0.8728,
"failureCount": 152,
"failureRate": 0.8736,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1272,
"total": 173,
"unresolvedFailureCount": 107
"successRate": 0.1264,
"total": 174,
"unresolvedFailureCount": 108
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 61,
@@ -5837,22 +5837,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 24,
"model_load": 13,
"repository_structure": 5,
"runtime_memory": 19,
"参数/模板问题": 11
},
"failureCount": 118,
"failureCount": 119,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 118,
"unresolvedFailureCount": 57
"total": 119,
"unresolvedFailureCount": 58
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 47,
@@ -5932,7 +5932,7 @@
"unresolvedFailureCount": 233
}
},
"generatedAt": "2026-10-05T04:45:06.189261+00:00",
"generatedAt": "2026-10-05T04:54:31.118126+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -6025,7 +6025,7 @@
"decisionSuccessRate": 0.0889,
"decisionTotal": 832,
"failureBreakdown": {
"ambiguous_runtime": 512,
"ambiguous_runtime": 513,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 310,
@@ -6038,15 +6038,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1628,
"failureCount": 1629,
"failureRate": 0.9565,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0435,
"total": 1702,
"unresolvedFailureCount": 854
"total": 1703,
"unresolvedFailureCount": 855
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 64,
@@ -6330,7 +6330,7 @@
"decisionSuccessRate": 0.0463,
"decisionTotal": 777,
"failureBreakdown": {
"ambiguous_runtime": 344,
"ambiguous_runtime": 345,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
@@ -6345,15 +6345,15 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1574,
"failureRate": 0.9776,
"failureCount": 1575,
"failureRate": 0.9777,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0224,
"total": 1610,
"unresolvedFailureCount": 829
"successRate": 0.0223,
"total": 1611,
"unresolvedFailureCount": 830
}
},
"observedGpuMemoryGiB": {
@@ -11808,9 +11808,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
@@ -11822,8 +11822,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao": {
"attributableFailureCount": 0,
@@ -23736,6 +23736,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "gemma4_unified",
"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|gemma4_unified|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -37627,6 +37650,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -55398,6 +55445,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gemma4_unified",
"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|gemma4_unified|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -57251,15 +57322,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17320,
"totalRecords": 17544,
"terminalRecords": 17322,
"totalRecords": 17546,
"totals": {
"attributableFailureCount": 6225,
"decisionFailureRate": 0.8642,
"decisionSuccessRate": 0.1358,
"decisionTotal": 7203,
"failureBreakdown": {
"ambiguous_runtime": 4538,
"ambiguous_runtime": 4540,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -57275,15 +57346,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16342,
"failureCount": 16344,
"failureRate": 0.9435,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 951,
"successCount": 978,
"successRate": 0.0565,
"total": 17320,
"unresolvedFailureCount": 9166
"total": 17322,
"unresolvedFailureCount": 9168
},
"warnings": [
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -57343,6 +57414,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17544,
"summarizedRecords": 17546,
"version": 1
}