state: generation 16700 (cycle)

This commit is contained in:
2026-09-26 17:20:54 +00:00
parent 8ca2e937c4
commit 81b7ee53f2
8 changed files with 1610 additions and 1518 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-26T17:14:27.607568+00:00",
"lastSyncTime": "2026-09-26T17:14:27.552028+00:00",
"generatedAt": "2026-09-26T17:19:54.419455+00:00",
"lastSyncTime": "2026-09-26T17:19:54.158491+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5409,34 +5409,34 @@
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 14,
"platform_infrastructure": 19,
"platform_infrastructure": 20,
"tokenizer_compatibility": 88,
"参数/模板问题": 6
},
"failureCount": 136,
"failureCount": 137,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 19,
"platformFailureCount": 20,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 136,
"total": 137,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 613,
"attributableFailureCount": 614,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 613,
"decisionTotal": 614,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 27,
"context_length": 34,
"framework_architecture_unsupported": 141,
"framework_architecture_unsupported": 142,
"memory_capacity": 113,
"platform_infrastructure": 205,
"repository_structure": 75,
@@ -5444,7 +5444,7 @@
"tokenizer_compatibility": 179,
"参数/模板问题": 9
},
"failureCount": 936,
"failureCount": 937,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -5454,7 +5454,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 936,
"total": 937,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5956,17 +5956,17 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3621,
"attributableFailureCount": 3622,
"decisionFailureRate": 0.9739,
"decisionSuccessRate": 0.0261,
"decisionTotal": 3718,
"decisionTotal": 3719,
"failureBreakdown": {
"ambiguous_runtime": 1574,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 92,
"context_length": 161,
"framework_architecture_unsupported": 1356,
"framework_architecture_unsupported": 1357,
"memory_capacity": 725,
"model_load": 220,
"platform_infrastructure": 869,
@@ -5975,14 +5975,14 @@
"tokenizer_compatibility": 416,
"参数/模板问题": 50
},
"failureCount": 6114,
"failureCount": 6115,
"failureRate": 0.9844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 869,
"successCount": 97,
"successRate": 0.0156,
"total": 6211,
"total": 6212,
"unresolvedFailureCount": 1624
},
"vllm-customized": {
@@ -6090,18 +6090,18 @@
"framework_architecture_unsupported": 32,
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 19,
"platform_infrastructure": 20,
"tokenizer_compatibility": 88,
"参数/模板问题": 13
},
"failureCount": 499,
"failureCount": 500,
"failureRate": 0.9901,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 19,
"platformFailureCount": 20,
"successCount": 5,
"successRate": 0.0099,
"total": 504,
"total": 505,
"unresolvedFailureCount": 332
},
"vllm_tokenizer_patch": {
@@ -6133,7 +6133,7 @@
"unresolvedFailureCount": 196
}
},
"generatedAt": "2026-09-26T17:14:27.595531+00:00",
"generatedAt": "2026-09-26T17:19:54.406878+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6468,32 +6468,32 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 743,
"decisionFailureRate": 0.8888,
"decisionSuccessRate": 0.1112,
"decisionTotal": 836,
"attributableFailureCount": 744,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 837,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 36,
"context_length": 39,
"framework_architecture_unsupported": 157,
"framework_architecture_unsupported": 158,
"memory_capacity": 113,
"platform_infrastructure": 224,
"platform_infrastructure": 225,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 270,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1389,
"failureRate": 0.9372,
"failureCount": 1391,
"failureRate": 0.9373,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 224,
"platformFailureCount": 225,
"successCount": 93,
"successRate": 0.0628,
"total": 1482,
"successRate": 0.0627,
"total": 1484,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -20613,6 +20613,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -20705,6 +20728,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -47903,6 +47949,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -48071,6 +48141,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -50813,23 +50907,23 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17040,
"totalRecords": 17261,
"terminalRecords": 17042,
"totalRecords": 17263,
"totals": {
"attributableFailureCount": 6110,
"attributableFailureCount": 6111,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7076,
"decisionTotal": 7077,
"failureBreakdown": {
"ambiguous_runtime": 4407,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 127,
"context_length": 322,
"framework_architecture_unsupported": 2170,
"framework_architecture_unsupported": 2171,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 935,
"platform_infrastructure": 936,
"repository_structure": 742,
"runtime_memory": 100,
"tokenizer_compatibility": 678,
@@ -50837,30 +50931,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16074,
"failureCount": 16076,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 935,
"platformFailureCount": 936,
"successCount": 966,
"successRate": 0.0567,
"total": 17040,
"total": 17042,
"unresolvedFailureCount": 9029
},
"warnings": [
"GPU Biren_166m 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 Iluvatar_bi-100 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 Iluvatar_bi-150 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 Mthreads_s4000 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 Ascend_910-b3 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 hygon_k100-ai 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 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 MetaX_c-500 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。",
"组合 Iluvatar_bi-150|llamacpp|text-generation 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|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50873,6 +50967,7 @@
"组合 Iluvatar_bi-100|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-b4|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 Cambricon_mlu-370-x4|vllm-mlu|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。",
"组合 hygon_k100-ai|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-b4|vllm_tokenizer_patch|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|vllm-customized|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50898,11 +50993,10 @@
"组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|llamacpp|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|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 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。",
"组合 MetaX_c-500|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17261,
"summarizedRecords": 17263,
"version": 1
}