state: generation 8367 (cycle)

This commit is contained in:
2026-09-16 19:56:50 +00:00
parent 753553bb32
commit 7543499431
10 changed files with 2100 additions and 2077 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T19:45:32.258486+00:00",
"lastSyncTime": "2026-09-16T19:45:29.643298+00:00",
"generatedAt": "2026-09-16T19:54:49.143345+00:00",
"lastSyncTime": "2026-09-16T19:54:46.652476+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1900,54 +1900,54 @@
"unresolvedFailureCount": 42
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 37,
"decisionFailureRate": 0.9487,
"decisionSuccessRate": 0.0513,
"decisionTotal": 39,
"attributableFailureCount": 38,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"runtime_memory": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 96,
"failureRate": 0.9796,
"failureCount": 97,
"failureRate": 0.9798,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0204,
"successRate": 0.0202,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 98,
"total": 99,
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 17,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"attributableFailureCount": 18,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 19,
"failureBreakdown": {
"framework_architecture_unsupported": 12,
"framework_architecture_unsupported": 13,
"model_load": 5
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 18,
"failureRate": 0.9474,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0526,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 18,
"total": 19,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2761,10 +2761,10 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 184,
"decisionFailureRate": 0.7449,
"decisionSuccessRate": 0.2551,
"decisionTotal": 247,
"attributableFailureCount": 185,
"decisionFailureRate": 0.746,
"decisionSuccessRate": 0.254,
"decisionTotal": 248,
"failureBreakdown": {
"ambiguous_runtime": 157,
"backend_operator": 4,
@@ -2772,30 +2772,30 @@
"memory_capacity": 5,
"model_load": 46,
"platform_infrastructure": 1,
"runtime_memory": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 5,
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1088,
"failureCount": 1089,
"failureRate": 0.9453,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 63,
"successRate": 0.0547,
"total": 1151,
"total": 1152,
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 372,
"decisionFailureRate": 0.9612,
"decisionSuccessRate": 0.0388,
"decisionTotal": 387,
"attributableFailureCount": 373,
"decisionFailureRate": 0.9613,
"decisionSuccessRate": 0.0387,
"decisionTotal": 388,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 276,
"framework_architecture_unsupported": 277,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2804,14 +2804,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 627,
"failureRate": 0.9766,
"failureCount": 628,
"failureRate": 0.9767,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0234,
"total": 642,
"successRate": 0.0233,
"total": 643,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2922,7 +2922,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T19:45:32.252226+00:00",
"generatedAt": "2026-09-16T19:54:49.138247+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2973,29 +2973,29 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 54,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 57,
"attributableFailureCount": 56,
"decisionFailureRate": 0.9492,
"decisionSuccessRate": 0.0508,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 39,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 113,
"failureRate": 0.9741,
"failureCount": 115,
"failureRate": 0.9746,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0259,
"total": 116,
"successRate": 0.0254,
"total": 118,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3621,14 +3621,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -3640,7 +3640,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
@@ -6298,32 +6298,32 @@
"unresolvedFailureCount": 7
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 11,
"consecutiveFailures": 5,
"attributableFailureCount": 12,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 9,
"model_load": 1,
"runtime_memory": 1,
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 18,
"failureRate": 0.9474,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T19:45:29.643282+00:00",
"lastTerminalAt": "2026-09-16T19:54:46.652476+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0526,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 18,
"total": 19,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7312,6 +7312,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11115,34 +11139,34 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2042,
"totalRecords": 2136,
"terminalRecords": 2044,
"totalRecords": 2138,
"totals": {
"attributableFailureCount": 660,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 741,
"attributableFailureCount": 662,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 743,
"failureBreakdown": {
"ambiguous_runtime": 494,
"backend_operator": 45,
"framework_architecture_unsupported": 434,
"framework_architecture_unsupported": 435,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
"repository_structure": 8,
"runtime_memory": 16,
"runtime_memory": 17,
"tokenizer_compatibility": 60,
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1961,
"failureRate": 0.9603,
"failureCount": 1963,
"failureRate": 0.9604,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 81,
"successRate": 0.0397,
"total": 2042,
"successRate": 0.0396,
"total": 2044,
"unresolvedFailureCount": 1291
},
"warnings": [
@@ -11150,14 +11174,14 @@
"GPU Iluvatar_mrv-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-b4 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 Biren_166m 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 hygon_k100-ai 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 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 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 Biren_166m|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 Biren_166m|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 Vastai_va16|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。",
@@ -11182,6 +11206,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2136,
"summarizedRecords": 2138,
"version": 1
}