state: generation 18454 (cycle)

This commit is contained in:
2026-09-29 16:43:45 +00:00
parent 03829af865
commit 15730dc67a
8 changed files with 1624 additions and 1586 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-29T16:17:37.730197+00:00",
"lastSyncTime": "2026-09-29T16:17:37.246258+00:00",
"generatedAt": "2026-09-29T16:41:41.433674+00:00",
"lastSyncTime": "2026-09-29T16:41:41.155395+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3717,10 +3717,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 111,
"ambiguous_runtime": 112,
"memory_capacity": 1
},
"failureCount": 112,
"failureCount": 113,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3730,8 +3730,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 112,
"unresolvedFailureCount": 111
"total": 113,
"unresolvedFailureCount": 112
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 45,
@@ -3859,29 +3859,29 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 15,
"decisionFailureRate": 0.6522,
"decisionSuccessRate": 0.3478,
"decisionTotal": 23,
"attributableFailureCount": 16,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 43,
"framework_architecture_unsupported": 12,
"framework_architecture_unsupported": 13,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 63,
"failureRate": 0.8873,
"failureCount": 64,
"failureRate": 0.8889,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.1127,
"successRate": 0.1111,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 71,
"total": 72,
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -5448,9 +5448,9 @@
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 617,
"decisionFailureRate": 0.9984,
"decisionSuccessRate": 0.0016,
"decisionTotal": 618,
"decisionFailureRate": 0.9968,
"decisionSuccessRate": 0.0032,
"decisionTotal": 619,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
@@ -5465,16 +5465,16 @@
"参数/模板问题": 9
},
"failureCount": 944,
"failureRate": 0.9989,
"failureRate": 0.9979,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 209,
"successCount": 1,
"successRate": 0.0011,
"successCount": 2,
"successRate": 0.0021,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 945,
"total": 946,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5977,9 +5977,9 @@
},
"vllm": {
"attributableFailureCount": 3630,
"decisionFailureRate": 0.9735,
"decisionSuccessRate": 0.0265,
"decisionTotal": 3729,
"decisionFailureRate": 0.9732,
"decisionSuccessRate": 0.0268,
"decisionTotal": 3730,
"failureBreakdown": {
"ambiguous_runtime": 1587,
"architecture_compatibility": 112,
@@ -5996,13 +5996,13 @@
"参数/模板问题": 50
},
"failureCount": 6140,
"failureRate": 0.9841,
"failureRate": 0.984,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 873,
"successCount": 99,
"successRate": 0.0159,
"total": 6239,
"successCount": 100,
"successRate": 0.016,
"total": 6240,
"unresolvedFailureCount": 1637
},
"vllm-customized": {
@@ -6029,27 +6029,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.58,
"decisionSuccessRate": 0.42,
"decisionTotal": 50,
"attributableFailureCount": 30,
"decisionFailureRate": 0.5882,
"decisionSuccessRate": 0.4118,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 91,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"model_load": 5,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 128,
"failureRate": 0.8591,
"failureCount": 129,
"failureRate": 0.86,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 21,
"successRate": 0.1409,
"total": 149,
"successRate": 0.14,
"total": 150,
"unresolvedFailureCount": 98
},
"vllm-patch-tokenizer": {
@@ -6105,7 +6105,7 @@
"decisionSuccessRate": 0.0312,
"decisionTotal": 160,
"failureBreakdown": {
"ambiguous_runtime": 328,
"ambiguous_runtime": 329,
"backend_operator": 9,
"framework_architecture_unsupported": 36,
"memory_capacity": 10,
@@ -6114,15 +6114,15 @@
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 518,
"failureRate": 0.9904,
"failureCount": 519,
"failureRate": 0.9905,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0096,
"total": 523,
"unresolvedFailureCount": 341
"successRate": 0.0095,
"total": 524,
"unresolvedFailureCount": 342
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 131,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 203
}
},
"generatedAt": "2026-09-29T16:17:37.716802+00:00",
"generatedAt": "2026-09-29T16:41:41.418509+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 104,
@@ -6215,7 +6215,7 @@
"decisionSuccessRate": 0.1174,
"decisionTotal": 213,
"failureBreakdown": {
"ambiguous_runtime": 254,
"ambiguous_runtime": 255,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 121,
@@ -6229,26 +6229,26 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 747,
"failureRate": 0.9676,
"failureCount": 748,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0324,
"total": 772,
"unresolvedFailureCount": 557
"successRate": 0.0323,
"total": 773,
"unresolvedFailureCount": 558
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 747,
"decisionFailureRate": 0.911,
"decisionSuccessRate": 0.089,
"decisionTotal": 820,
"attributableFailureCount": 748,
"decisionFailureRate": 0.9111,
"decisionSuccessRate": 0.0889,
"decisionTotal": 821,
"failureBreakdown": {
"ambiguous_runtime": 508,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 300,
"framework_architecture_unsupported": 301,
"memory_capacity": 219,
"model_load": 7,
"platform_infrastructure": 16,
@@ -6258,14 +6258,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1613,
"failureCount": 1614,
"failureRate": 0.9567,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0433,
"total": 1686,
"total": 1687,
"unresolvedFailureCount": 850
},
"Cambricon_mlu-370-x8": {
@@ -6489,9 +6489,9 @@
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 753,
"decisionFailureRate": 0.889,
"decisionSuccessRate": 0.111,
"decisionTotal": 847,
"decisionFailureRate": 0.888,
"decisionSuccessRate": 0.112,
"decisionTotal": 848,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -6507,13 +6507,13 @@
"验证失败": 32
},
"failureCount": 1406,
"failureRate": 0.9373,
"failureRate": 0.9367,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 231,
"successCount": 94,
"successRate": 0.0627,
"total": 1500,
"successCount": 95,
"successRate": 0.0633,
"total": 1501,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -9793,9 +9793,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
@@ -9807,8 +9807,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -11147,14 +11147,14 @@
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none": {
"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-mlu",
"modelType": "qwen3_5_moe",
@@ -11166,7 +11166,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
@@ -21397,7 +21397,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -21407,11 +21407,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successCount": 2,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": {
@@ -32451,9 +32451,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
@@ -32466,8 +32466,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
@@ -34453,6 +34453,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -50008,6 +50032,28 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -52822,20 +52868,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17118,
"totalRecords": 17339,
"terminalRecords": 17121,
"totalRecords": 17342,
"totals": {
"attributableFailureCount": 6135,
"decisionFailureRate": 0.8634,
"decisionSuccessRate": 0.1366,
"decisionTotal": 7106,
"attributableFailureCount": 6136,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7108,
"failureBreakdown": {
"ambiguous_runtime": 4447,
"ambiguous_runtime": 4448,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 323,
"framework_architecture_unsupported": 2188,
"framework_architecture_unsupported": 2189,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 942,
@@ -52846,15 +52892,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16147,
"failureRate": 0.9433,
"failureCount": 16149,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 942,
"successCount": 971,
"successRate": 0.0567,
"total": 17118,
"unresolvedFailureCount": 9070
"successCount": 972,
"successRate": 0.0568,
"total": 17121,
"unresolvedFailureCount": 9071
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -52883,7 +52929,6 @@
"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。",
"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 Iluvatar_mrv-100|unknown|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 Kunlunxin_p-800|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 MetaX_c-500|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 Ascend_910-b4|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -52908,10 +52953,11 @@
"组合 hygon_k100-ai|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 Cambricon_mlu-370-x4|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 Ascend_910-b3|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。",
"组合 Vastai_va16|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|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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17339,
"summarizedRecords": 17342,
"version": 1
}