state: generation 11543 (cycle)

This commit is contained in:
2026-09-21 15:58:20 +00:00
parent 9ed4876b56
commit 5183a33e19
10 changed files with 2109 additions and 2017 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T15:54:38.201498+00:00",
"lastSyncTime": "2026-09-21T15:54:37.859039+00:00",
"generatedAt": "2026-09-21T15:58:05.029156+00:00",
"lastSyncTime": "2026-09-21T15:58:04.749297+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4315,13 +4315,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 74,
"ambiguous_runtime": 75,
"memory_capacity": 1,
"参数/模板问题": 4,
"日志缺失": 1,
"验证失败": 22
},
"failureCount": 102,
"failureCount": 103,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -4331,8 +4331,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 102,
"unresolvedFailureCount": 101
"total": 103,
"unresolvedFailureCount": 102
},
"Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -4362,10 +4362,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 100,
"ambiguous_runtime": 101,
"参数/模板问题": 3
},
"failureCount": 103,
"failureCount": 104,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4375,21 +4375,22 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 103,
"unresolvedFailureCount": 103
"total": 104,
"unresolvedFailureCount": 104
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 15,
"attributableFailureCount": 16,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 14,
"repository_structure": 1,
"参数/模板问题": 12
},
"failureCount": 28,
"failureCount": 29,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -4399,7 +4400,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 28,
"total": 29,
"unresolvedFailureCount": 13
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -5355,7 +5356,7 @@
"decisionSuccessRate": 0.304,
"decisionTotal": 2671,
"failureBreakdown": {
"ambiguous_runtime": 1965,
"ambiguous_runtime": 1966,
"architecture_compatibility": 100,
"backend_operator": 5,
"context_length": 157,
@@ -5370,15 +5371,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 8346,
"failureCount": 8347,
"failureRate": 0.9113,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 812,
"successRate": 0.0887,
"total": 9158,
"unresolvedFailureCount": 6445
"total": 9159,
"unresolvedFailureCount": 6446
},
"vllm": {
"attributableFailureCount": 3531,
@@ -5507,7 +5508,7 @@
"decisionSuccessRate": 0.0391,
"decisionTotal": 128,
"failureBreakdown": {
"ambiguous_runtime": 168,
"ambiguous_runtime": 169,
"backend_operator": 8,
"framework_architecture_unsupported": 23,
"memory_capacity": 7,
@@ -5516,21 +5517,21 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 321,
"failureCount": 322,
"failureRate": 0.9847,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0153,
"total": 326,
"unresolvedFailureCount": 181
"total": 327,
"unresolvedFailureCount": 182
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 72,
"attributableFailureCount": 71,
"decisionFailureRate": 0.9726,
"decisionSuccessRate": 0.0274,
"decisionTotal": 73,
"failureBreakdown": {
"ambiguous_runtime": 65,
"backend_operator": 1,
@@ -5539,22 +5540,22 @@
"memory_capacity": 1,
"model_load": 2,
"platform_infrastructure": 1,
"repository_structure": 1,
"repository_structure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 26
},
"failureCount": 162,
"failureRate": 0.9878,
"failureCount": 163,
"failureRate": 0.9879,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0122,
"total": 164,
"successRate": 0.0121,
"total": 165,
"unresolvedFailureCount": 91
}
},
"generatedAt": "2026-09-21T15:54:38.191412+00:00",
"generatedAt": "2026-09-21T15:58:05.018957+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 95,
@@ -5779,28 +5780,29 @@
"unresolvedFailureCount": 716
},
"Kunlunxin_p-800": {
"attributableFailureCount": 17,
"attributableFailureCount": 18,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 176,
"ambiguous_runtime": 178,
"backend_operator": 1,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"repository_structure": 1,
"参数/模板问题": 19,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 236,
"failureCount": 239,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 236,
"unresolvedFailureCount": 219
"total": 239,
"unresolvedFailureCount": 221
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -13005,6 +13007,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|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": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -13627,6 +13652,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|aquila3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "aquila3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16845,14 +16893,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"参数/模板问题": 4
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T04:36:00.569197+00:00",
"lastTerminalAt": "2026-09-21T15:58:04.749250+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -16860,8 +16908,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -16871,9 +16919,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -16885,21 +16933,22 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"repository_structure": 1,
"参数/模板问题": 3
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -16911,7 +16960,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 3
},
"MetaX_c-500|unknown|text-generation": {
@@ -17068,17 +17117,16 @@
"unresolvedFailureCount": 9
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"repository_structure": 1
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
@@ -17090,7 +17138,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
@@ -19737,10 +19785,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 2,
"memory_capacity": 1
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T13:30:42.156001+00:00",
@@ -19753,8 +19801,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 3
"total": 3,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 0,
@@ -19806,31 +19854,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"memory_capacity": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T11:37:54.215258+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
@@ -20131,6 +20154,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-21T15:58:04.749297+00:00",
"modelType": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -20181,6 +20229,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|aquila3|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T15:58:04.749283+00:00",
"modelType": "aquila3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -20406,31 +20479,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mpt|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-21T14:32:55.759786+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|llama|awq": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -30354,6 +30402,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -31555,6 +31627,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|aquila3|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 12,
"modelType": "aquila3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -35433,15 +35529,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16303,
"totalRecords": 16491,
"terminalRecords": 16306,
"totalRecords": 16494,
"totals": {
"attributableFailureCount": 5890,
"attributableFailureCount": 5891,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6836,
"decisionTotal": 6837,
"failureBreakdown": {
"ambiguous_runtime": 3960,
"ambiguous_runtime": 3962,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
@@ -35450,38 +35546,38 @@
"memory_capacity": 1197,
"model_load": 498,
"platform_infrastructure": 925,
"repository_structure": 737,
"repository_structure": 738,
"runtime_memory": 85,
"tokenizer_compatibility": 661,
"参数/模板问题": 3189,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15357,
"failureCount": 15360,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.058,
"total": 16303,
"unresolvedFailureCount": 8542
"total": 16306,
"unresolvedFailureCount": 8544
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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 MetaX_c-500 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-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-b3 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 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 hygon_k100-ai 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 MetaX_c-500 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。",
"组合 Iluvatar_bi-150|vllm|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 Sunrise_pt-200-x1|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。",
"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。",
@@ -35521,6 +35617,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16491,
"summarizedRecords": 16494,
"version": 1
}