state: generation 16733 (cycle)

This commit is contained in:
2026-09-26 18:29:46 +00:00
parent 60d9d0410f
commit 706f46db09
8 changed files with 1603 additions and 1557 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-26T18:22:15.111319+00:00",
"lastSyncTime": "2026-09-26T18:22:14.859595+00:00",
"generatedAt": "2026-09-26T18:28:52.859100+00:00",
"lastSyncTime": "2026-09-26T18:28:52.569178+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5427,14 +5427,14 @@
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 614,
"attributableFailureCount": 615,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 614,
"decisionTotal": 615,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 27,
"backend_operator": 28,
"context_length": 34,
"framework_architecture_unsupported": 142,
"memory_capacity": 113,
@@ -5444,7 +5444,7 @@
"tokenizer_compatibility": 179,
"参数/模板问题": 9
},
"failureCount": 938,
"failureCount": 939,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -5454,7 +5454,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 938,
"total": 939,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5956,15 +5956,15 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3622,
"attributableFailureCount": 3623,
"decisionFailureRate": 0.9739,
"decisionSuccessRate": 0.0261,
"decisionTotal": 3719,
"decisionTotal": 3720,
"failureBreakdown": {
"ambiguous_runtime": 1574,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 92,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1357,
"memory_capacity": 725,
@@ -5975,14 +5975,14 @@
"tokenizer_compatibility": 416,
"参数/模板问题": 50
},
"failureCount": 6116,
"failureCount": 6117,
"failureRate": 0.9844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 870,
"successCount": 97,
"successRate": 0.0156,
"total": 6213,
"total": 6214,
"unresolvedFailureCount": 1624
},
"vllm-customized": {
@@ -6133,7 +6133,7 @@
"unresolvedFailureCount": 196
}
},
"generatedAt": "2026-09-26T18:22:15.098384+00:00",
"generatedAt": "2026-09-26T18:28:52.846993+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6468,14 +6468,14 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 745,
"decisionFailureRate": 0.889,
"decisionSuccessRate": 0.111,
"decisionTotal": 838,
"attributableFailureCount": 746,
"decisionFailureRate": 0.8892,
"decisionSuccessRate": 0.1108,
"decisionTotal": 839,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 36,
"backend_operator": 37,
"context_length": 39,
"framework_architecture_unsupported": 158,
"memory_capacity": 113,
@@ -6486,14 +6486,14 @@
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1393,
"failureRate": 0.9374,
"failureCount": 1394,
"failureRate": 0.9375,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 226,
"successCount": 93,
"successRate": 0.0626,
"total": 1486,
"successRate": 0.0625,
"total": 1487,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -20659,6 +20659,29 @@
"total": 3,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -48021,6 +48044,30 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 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": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -50908,18 +50955,18 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17044,
"totalRecords": 17265,
"terminalRecords": 17045,
"totalRecords": 17266,
"totals": {
"attributableFailureCount": 6112,
"attributableFailureCount": 6113,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7078,
"decisionTotal": 7079,
"failureBreakdown": {
"ambiguous_runtime": 4407,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 127,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2171,
"memory_capacity": 1206,
@@ -50932,30 +50979,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16078,
"failureCount": 16079,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 937,
"successCount": 966,
"successRate": 0.0567,
"total": 17044,
"total": 17045,
"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 Iluvatar_bi-150 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 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 Ascend_910-b3 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-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 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 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 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。",
@@ -50968,7 +51015,6 @@
"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。",
@@ -50994,10 +51040,11 @@
"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": 17265,
"summarizedRecords": 17266,
"version": 1
}