state: generation 11208 (cycle)

This commit is contained in:
2026-09-21 05:21:37 +00:00
parent 900044829d
commit 2474c53318
9 changed files with 1901 additions and 1817 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T05:17:51.754913+00:00",
"lastSyncTime": "2026-09-21T05:17:51.457662+00:00",
"generatedAt": "2026-09-21T05:21:26.483682+00:00",
"lastSyncTime": "2026-09-21T05:21:25.760211+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1739,7 +1739,7 @@
"kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 6,
"evidenceCount": 3,
"expiresAt": "2026-10-20T03:09:17.939093+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T03:09:17.939093+00:00",
@@ -1749,16 +1749,12 @@
"sourceModelIds": [
"mlx-community/XYZ-Aquila-mini-OptiQ-4bit",
"apodex/Apodex-1.1-mini-GPTQ-Int4",
"cyankiwi/Apodex-1.1-mini-AWQ-INT4",
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B",
"primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8"
"cyankiwi/Apodex-1.1-mini-AWQ-INT4"
],
"sourceTaskIds": [
"4969329",
"4969320",
"4969047",
"4969042",
"4969040"
"4969047"
],
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation"
@@ -3310,9 +3306,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 41
"ambiguous_runtime": 44
},
"failureCount": 41,
"failureCount": 44,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -3322,8 +3318,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 41,
"unresolvedFailureCount": 41
"total": 44,
"unresolvedFailureCount": 44
},
"Iluvatar_bi-100|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -5086,7 +5082,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 655,
"failureBreakdown": {
"ambiguous_runtime": 155,
"ambiguous_runtime": 156,
"architecture_compatibility": 30,
"attention_backend": 1,
"context_length": 42,
@@ -5098,7 +5094,7 @@
"runtime_memory": 53,
"tokenizer_compatibility": 79
},
"failureCount": 813,
"failureCount": 814,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -5108,8 +5104,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 813,
"unresolvedFailureCount": 155
"total": 814,
"unresolvedFailureCount": 156
},
"hygon_k100-ai|vllm|unknown": {
"attributableFailureCount": 1,
@@ -5184,21 +5180,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 53,
"framework_architecture_unsupported": 7,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 8
},
"failureCount": 72,
"failureCount": 75,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 72,
"unresolvedFailureCount": 50
"total": 75,
"unresolvedFailureCount": 53
},
"unknown": {
"attributableFailureCount": 1858,
@@ -5237,7 +5233,7 @@
"decisionSuccessRate": 0.0233,
"decisionTotal": 3600,
"failureBreakdown": {
"ambiguous_runtime": 1467,
"ambiguous_runtime": 1468,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5251,15 +5247,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 41
},
"failureCount": 5889,
"failureCount": 5890,
"failureRate": 0.9859,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 84,
"successRate": 0.0141,
"total": 5973,
"unresolvedFailureCount": 1508
"total": 5974,
"unresolvedFailureCount": 1509
},
"vllm-customized": {
"attributableFailureCount": 3,
@@ -5399,7 +5395,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T05:17:51.744207+00:00",
"generatedAt": "2026-09-21T05:21:26.472937+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5544,22 +5540,22 @@
"decisionSuccessRate": 0.2392,
"decisionTotal": 255,
"failureBreakdown": {
"ambiguous_runtime": 161,
"ambiguous_runtime": 164,
"memory_capacity": 194,
"platform_infrastructure": 635,
"参数/模板问题": 242,
"日志缺失": 134,
"验证失败": 20
},
"failureCount": 1386,
"failureRate": 0.9578,
"failureCount": 1389,
"failureRate": 0.9579,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 635,
"successCount": 61,
"successRate": 0.0422,
"total": 1447,
"unresolvedFailureCount": 557
"successRate": 0.0421,
"total": 1450,
"unresolvedFailureCount": 560
},
"Iluvatar_bi-150": {
"attributableFailureCount": 739,
@@ -5787,7 +5783,7 @@
"decisionSuccessRate": 0.0413,
"decisionTotal": 727,
"failureBreakdown": {
"ambiguous_runtime": 302,
"ambiguous_runtime": 303,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
@@ -5802,15 +5798,15 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1481,
"failureRate": 0.9801,
"failureCount": 1482,
"failureRate": 0.9802,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 30,
"successRate": 0.0199,
"total": 1511,
"unresolvedFailureCount": 780
"successRate": 0.0198,
"total": 1512,
"unresolvedFailureCount": 781
}
},
"observedGpuMemoryGiB": {
@@ -9310,9 +9306,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 3
},
"failureCount": 1,
"failureCount": 3,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "gemma4",
@@ -9324,8 +9320,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -9356,9 +9352,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "qwen3_5",
@@ -9370,8 +9366,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
@@ -14545,6 +14541,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -14937,13 +14956,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 9
},
"failureCount": 6,
"failureCount": 9,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:17:51.457662+00:00",
"lastTerminalAt": "2026-09-21T05:21:25.760211+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -14951,8 +14970,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 9,
"unresolvedFailureCount": 9
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 14,
@@ -15167,18 +15186,18 @@
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 8,
"参数/模板问题": 11
"framework_architecture_unsupported": 5,
"参数/模板问题": 10
},
"failureCount": 20,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -15190,8 +15209,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 12
"total": 16,
"unresolvedFailureCount": 11
},
"Kunlunxin_p-800|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -15432,12 +15451,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 6,
"model_load": 2,
"runtime_memory": 1
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -15449,8 +15468,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 4
"total": 14,
"unresolvedFailureCount": 5
}
},
"recentProfileCombinationStats": {
@@ -17038,12 +17057,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 3
},
"failureCount": 1,
"failureCount": 3,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:17:51.457647+00:00",
"lastTerminalAt": "2026-09-21T05:21:25.760211+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -17053,8 +17072,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -17088,9 +17107,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-21T05:17:51.457611+00:00",
@@ -17103,8 +17122,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
@@ -18811,15 +18830,15 @@
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 1
},
"failureCount": 3,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T20:49:19.683231+00:00",
@@ -18832,7 +18851,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|gptq": {
@@ -18861,15 +18880,15 @@
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T03:45:50.542852+00:00",
@@ -18882,7 +18901,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
@@ -19208,6 +19227,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T05:21:25.760184+00:00",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -24185,6 +24229,30 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|transformers|text-generation|gemma4|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 32,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|gemma4|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
@@ -24195,7 +24263,7 @@
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 32,
"loadSizeLog2Bucket": 34,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -24238,9 +24306,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 34,
@@ -24253,8 +24321,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 0,
@@ -31867,6 +31935,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen2|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation|qwen3|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -31940,15 +32032,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16138,
"totalRecords": 16319,
"terminalRecords": 16142,
"totalRecords": 16323,
"totals": {
"attributableFailureCount": 5854,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6794,
"failureBreakdown": {
"ambiguous_runtime": 3867,
"ambiguous_runtime": 3871,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -31964,31 +32056,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15198,
"failureCount": 15202,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 940,
"successRate": 0.0582,
"total": 16138,
"unresolvedFailureCount": 8421
"total": 16142,
"unresolvedFailureCount": 8425
},
"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 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 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。",
@@ -32027,6 +32119,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16319,
"summarizedRecords": 16323,
"version": 1
}