state: generation 19406 (cycle)

This commit is contained in:
2026-10-01 22:27:40 +00:00
parent c0087df935
commit 53dad84be5
10 changed files with 1368 additions and 1326 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-01T22:04:49.108094+00:00",
"lastSyncTime": "2026-10-01T22:04:48.852822+00:00",
"generatedAt": "2026-10-01T22:25:21.158774+00:00",
"lastSyncTime": "2026-10-01T22:25:20.867219+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3464,30 +3464,30 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 42,
"decisionFailureRate": 0.913,
"decisionSuccessRate": 0.087,
"decisionTotal": 46,
"attributableFailureCount": 43,
"decisionFailureRate": 0.9149,
"decisionSuccessRate": 0.0851,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 84,
"context_length": 8,
"ambiguous_runtime": 85,
"context_length": 9,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 135,
"failureRate": 0.9712,
"failureCount": 137,
"failureRate": 0.9716,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0288,
"successRate": 0.0284,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 139,
"unresolvedFailureCount": 92
"total": 141,
"unresolvedFailureCount": 93
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 70,
@@ -3780,10 +3780,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 118,
"ambiguous_runtime": 119,
"memory_capacity": 1
},
"failureCount": 119,
"failureCount": 120,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3793,8 +3793,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 119,
"unresolvedFailureCount": 118
"total": 120,
"unresolvedFailureCount": 119
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 45,
@@ -6169,7 +6169,7 @@
"decisionSuccessRate": 0.0305,
"decisionTotal": 164,
"failureBreakdown": {
"ambiguous_runtime": 341,
"ambiguous_runtime": 342,
"backend_operator": 9,
"framework_architecture_unsupported": 39,
"memory_capacity": 10,
@@ -6178,25 +6178,25 @@
"tokenizer_compatibility": 92,
"参数/模板问题": 13
},
"failureCount": 535,
"failureRate": 0.9907,
"failureCount": 536,
"failureRate": 0.9908,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0093,
"total": 540,
"unresolvedFailureCount": 354
"successRate": 0.0092,
"total": 541,
"unresolvedFailureCount": 355
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 142,
"decisionFailureRate": 0.9342,
"decisionSuccessRate": 0.0658,
"decisionTotal": 152,
"attributableFailureCount": 143,
"decisionFailureRate": 0.9346,
"decisionSuccessRate": 0.0654,
"decisionTotal": 153,
"failureBreakdown": {
"ambiguous_runtime": 196,
"ambiguous_runtime": 197,
"backend_operator": 15,
"context_length": 8,
"context_length": 9,
"framework_architecture_unsupported": 86,
"memory_capacity": 2,
"model_load": 23,
@@ -6206,27 +6206,27 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 370,
"failureRate": 0.9737,
"failureCount": 372,
"failureRate": 0.9738,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0263,
"total": 380,
"unresolvedFailureCount": 225
"successRate": 0.0262,
"total": 382,
"unresolvedFailureCount": 226
}
},
"generatedAt": "2026-10-01T22:04:49.095265+00:00",
"generatedAt": "2026-10-01T22:25:21.145863+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 113,
"decisionFailureRate": 0.837,
"decisionSuccessRate": 0.163,
"decisionTotal": 135,
"attributableFailureCount": 114,
"decisionFailureRate": 0.8382,
"decisionSuccessRate": 0.1618,
"decisionTotal": 136,
"failureBreakdown": {
"ambiguous_runtime": 152,
"context_length": 8,
"ambiguous_runtime": 153,
"context_length": 9,
"framework_architecture_unsupported": 99,
"memory_capacity": 2,
"platform_infrastructure": 1,
@@ -6236,15 +6236,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 335,
"failureRate": 0.9384,
"failureCount": 337,
"failureRate": 0.9387,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0616,
"total": 357,
"unresolvedFailureCount": 221
"successRate": 0.0613,
"total": 359,
"unresolvedFailureCount": 222
},
"Ascend_910-b4": {
"attributableFailureCount": 327,
@@ -6280,7 +6280,7 @@
"decisionSuccessRate": 0.1174,
"decisionTotal": 213,
"failureBreakdown": {
"ambiguous_runtime": 261,
"ambiguous_runtime": 262,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 121,
@@ -6294,15 +6294,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 754,
"failureCount": 755,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0321,
"total": 779,
"unresolvedFailureCount": 564
"total": 780,
"unresolvedFailureCount": 565
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 754,
@@ -6911,15 +6911,15 @@
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 17,
"context_length": 6
"context_length": 7
},
"failureCount": 23,
"failureCount": 24,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6931,7 +6931,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 23,
"total": 24,
"unresolvedFailureCount": 17
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
@@ -7607,9 +7607,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 16
"ambiguous_runtime": 17
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "starcoder2",
@@ -7621,8 +7621,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 16
"total": 17,
"unresolvedFailureCount": 17
},
"Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -9647,6 +9647,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -23917,9 +23940,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 10
"参数/模板问题": 8
},
"failureCount": 10,
"failureCount": 8,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -23931,22 +23954,22 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 10
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 14,
"context_length": 2,
"ambiguous_runtime": 15,
"context_length": 3,
"framework_architecture_unsupported": 2
},
"failureCount": 18,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -23958,8 +23981,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 14
"total": 20,
"unresolvedFailureCount": 15
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -24793,16 +24816,16 @@
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 6,
"context_length": 2
"context_length": 3
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T15:29:22.559035+00:00",
@@ -24815,7 +24838,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
@@ -24900,12 +24923,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T01:23:45.362492+00:00",
"lastTerminalAt": "2026-10-01T22:25:20.867219+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -24915,8 +24938,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -28446,15 +28469,15 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 2,
"context_length": 2
"context_length": 3
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
@@ -28467,7 +28490,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|31": {
@@ -29532,9 +29555,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
@@ -29547,8 +29570,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
@@ -32998,6 +33021,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none|35": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 35,
"modelType": "qwen3_5_moe_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -54522,19 +54569,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17210,
"totalRecords": 17431,
"terminalRecords": 17213,
"totalRecords": 17434,
"totals": {
"attributableFailureCount": 6171,
"attributableFailureCount": 6172,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7146,
"decisionTotal": 7147,
"failureBreakdown": {
"ambiguous_runtime": 4497,
"ambiguous_runtime": 4499,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"context_length": 327,
"framework_architecture_unsupported": 2214,
"memory_capacity": 1206,
"model_load": 553,
@@ -54546,30 +54593,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16235,
"failureRate": 0.9433,
"failureCount": 16238,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0567,
"total": 17210,
"unresolvedFailureCount": 9120
"successRate": 0.0566,
"total": 17213,
"unresolvedFailureCount": 9122
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Iluvatar_bi-100 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 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 Vastai_va16 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 Iluvatar_bi-150 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。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"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 Kunlunxin_p-800|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。",
@@ -54614,6 +54661,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17431,
"summarizedRecords": 17434,
"version": 1
}