state: generation 8364 (cycle)

This commit is contained in:
2026-09-16 19:48:02 +00:00
parent 009b944cac
commit 88678ccc42
11 changed files with 2157 additions and 2080 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T19:09:34.844010+00:00",
"lastSyncTime": "2026-09-16T19:09:33.045375+00:00",
"generatedAt": "2026-09-16T19:45:32.258486+00:00",
"lastSyncTime": "2026-09-16T19:45:29.643298+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1900,53 +1900,54 @@
"unresolvedFailureCount": 42
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 36,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 38,
"attributableFailureCount": 37,
"decisionFailureRate": 0.9487,
"decisionSuccessRate": 0.0513,
"decisionTotal": 39,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"runtime_memory": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 95,
"failureRate": 0.9794,
"failureCount": 96,
"failureRate": 0.9796,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0206,
"successRate": 0.0204,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 97,
"total": 98,
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 15,
"decisionFailureRate": 0.9375,
"decisionSuccessRate": 0.0625,
"decisionTotal": 16,
"attributableFailureCount": 17,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"framework_architecture_unsupported": 10,
"framework_architecture_unsupported": 12,
"model_load": 5
},
"failureCount": 15,
"failureRate": 0.9375,
"failureCount": 17,
"failureRate": 0.9444,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0625,
"successRate": 0.0556,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 16,
"total": 18,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2760,10 +2761,10 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 183,
"decisionFailureRate": 0.7439,
"decisionSuccessRate": 0.2561,
"decisionTotal": 246,
"attributableFailureCount": 184,
"decisionFailureRate": 0.7449,
"decisionSuccessRate": 0.2551,
"decisionTotal": 247,
"failureBreakdown": {
"ambiguous_runtime": 157,
"backend_operator": 4,
@@ -2771,29 +2772,30 @@
"memory_capacity": 5,
"model_load": 46,
"platform_infrastructure": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 5,
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1087,
"failureRate": 0.9452,
"failureCount": 1088,
"failureRate": 0.9453,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 63,
"successRate": 0.0548,
"total": 1150,
"successRate": 0.0547,
"total": 1151,
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 370,
"decisionFailureRate": 0.961,
"decisionSuccessRate": 0.039,
"decisionTotal": 385,
"attributableFailureCount": 372,
"decisionFailureRate": 0.9612,
"decisionSuccessRate": 0.0388,
"decisionTotal": 387,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 274,
"framework_architecture_unsupported": 276,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2802,14 +2804,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 625,
"failureCount": 627,
"failureRate": 0.9766,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0234,
"total": 640,
"total": 642,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2920,7 +2922,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T19:09:34.838356+00:00",
"generatedAt": "2026-09-16T19:45:32.252226+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2971,28 +2973,29 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 54,
"attributableFailureCount": 54,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 37,
"framework_architecture_unsupported": 39,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 110,
"failureRate": 0.9735,
"failureCount": 113,
"failureRate": 0.9741,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0265,
"total": 113,
"successRate": 0.0259,
"total": 116,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3617,7 +3620,7 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
"Biren_166m|vllm|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
@@ -3632,7 +3635,7 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
@@ -3640,6 +3643,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6272,31 +6298,32 @@
"unresolvedFailureCount": 7
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 4,
"attributableFailureCount": 11,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 9,
"model_load": 1,
"runtime_memory": 1,
"参数/模板问题": 1
},
"failureCount": 16,
"failureRate": 0.9412,
"failureCount": 17,
"failureRate": 0.9444,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T09:03:21.744792+00:00",
"lastTerminalAt": "2026-09-16T19:45:29.643282+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0588,
"successRate": 0.0556,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"total": 18,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7285,6 +7312,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|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": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7309,6 +7360,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|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": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11040,34 +11115,34 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2039,
"totalRecords": 2133,
"terminalRecords": 2042,
"totalRecords": 2136,
"totals": {
"attributableFailureCount": 657,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 738,
"attributableFailureCount": 660,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 741,
"failureBreakdown": {
"ambiguous_runtime": 494,
"backend_operator": 45,
"framework_architecture_unsupported": 432,
"framework_architecture_unsupported": 434,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
"repository_structure": 8,
"runtime_memory": 15,
"runtime_memory": 16,
"tokenizer_compatibility": 60,
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1958,
"failureCount": 1961,
"failureRate": 0.9603,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 81,
"successRate": 0.0397,
"total": 2039,
"total": 2042,
"unresolvedFailureCount": 1291
},
"warnings": [
@@ -11075,13 +11150,13 @@
"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 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 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。",
@@ -11107,6 +11182,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2133,
"summarizedRecords": 2136,
"version": 1
}