state: generation 18092 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-28T21:52:12.998878+00:00",
|
||||
"lastSyncTime": "2026-09-28T21:52:12.748435+00:00",
|
||||
"generatedAt": "2026-09-28T21:58:57.842255+00:00",
|
||||
"lastSyncTime": "2026-09-28T21:58:57.568298+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3717,10 +3717,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 109,
|
||||
"ambiguous_runtime": 110,
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 110,
|
||||
"failureCount": 111,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -3730,8 +3730,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 110,
|
||||
"unresolvedFailureCount": 109
|
||||
"total": 111,
|
||||
"unresolvedFailureCount": 110
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 45,
|
||||
@@ -3864,25 +3864,25 @@
|
||||
"decisionSuccessRate": 0.3636,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 41,
|
||||
"ambiguous_runtime": 42,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 60,
|
||||
"failureRate": 0.8824,
|
||||
"failureCount": 61,
|
||||
"failureRate": 0.8841,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1176,
|
||||
"successRate": 0.1159,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 68,
|
||||
"unresolvedFailureCount": 45
|
||||
"total": 69,
|
||||
"unresolvedFailureCount": 46
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -6034,7 +6034,7 @@
|
||||
"decisionSuccessRate": 0.4167,
|
||||
"decisionTotal": 48,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 89,
|
||||
"ambiguous_runtime": 90,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"model_load": 5,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -6042,15 +6042,15 @@
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 125,
|
||||
"failureRate": 0.8621,
|
||||
"failureCount": 126,
|
||||
"failureRate": 0.863,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 20,
|
||||
"successRate": 0.1379,
|
||||
"total": 145,
|
||||
"unresolvedFailureCount": 96
|
||||
"successRate": 0.137,
|
||||
"total": 146,
|
||||
"unresolvedFailureCount": 97
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 56,
|
||||
@@ -6105,7 +6105,7 @@
|
||||
"decisionSuccessRate": 0.0316,
|
||||
"decisionTotal": 158,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 324,
|
||||
"ambiguous_runtime": 325,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 34,
|
||||
"memory_capacity": 10,
|
||||
@@ -6114,15 +6114,15 @@
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 510,
|
||||
"failureCount": 511,
|
||||
"failureRate": 0.9903,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 20,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0097,
|
||||
"total": 515,
|
||||
"unresolvedFailureCount": 337
|
||||
"total": 516,
|
||||
"unresolvedFailureCount": 338
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 129,
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T21:52:12.986193+00:00",
|
||||
"generatedAt": "2026-09-28T21:58:57.829634+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6215,7 +6215,7 @@
|
||||
"decisionSuccessRate": 0.1174,
|
||||
"decisionTotal": 213,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 252,
|
||||
"ambiguous_runtime": 253,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 121,
|
||||
@@ -6229,15 +6229,15 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 745,
|
||||
"failureRate": 0.9675,
|
||||
"failureCount": 746,
|
||||
"failureRate": 0.9676,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0325,
|
||||
"total": 770,
|
||||
"unresolvedFailureCount": 555
|
||||
"successRate": 0.0324,
|
||||
"total": 771,
|
||||
"unresolvedFailureCount": 556
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 746,
|
||||
@@ -6245,7 +6245,7 @@
|
||||
"decisionSuccessRate": 0.0891,
|
||||
"decisionTotal": 819,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 506,
|
||||
"ambiguous_runtime": 507,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 299,
|
||||
@@ -6258,15 +6258,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1610,
|
||||
"failureRate": 0.9566,
|
||||
"failureCount": 1611,
|
||||
"failureRate": 0.9567,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0434,
|
||||
"total": 1683,
|
||||
"unresolvedFailureCount": 848
|
||||
"successRate": 0.0433,
|
||||
"total": 1684,
|
||||
"unresolvedFailureCount": 849
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -9450,9 +9450,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6
|
||||
"ambiguous_runtime": 7
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_moe",
|
||||
@@ -9464,8 +9464,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 6
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -10854,9 +10854,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9
|
||||
"ambiguous_runtime": 10
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "llama",
|
||||
@@ -10868,8 +10868,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -23210,10 +23210,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"ambiguous_runtime": 7,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 8,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23225,8 +23225,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -23598,17 +23598,16 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"runtime_memory": 1
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23620,7 +23619,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
@@ -24212,9 +24211,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastTerminalAt": "2026-09-26T05:44:29.660601+00:00",
|
||||
@@ -24227,8 +24226,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -31530,9 +31529,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
@@ -31545,8 +31544,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -33586,9 +33585,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
@@ -33601,8 +33600,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -51998,15 +51997,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17086,
|
||||
"totalRecords": 17307,
|
||||
"terminalRecords": 17088,
|
||||
"totalRecords": 17309,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6126,
|
||||
"decisionFailureRate": 0.8638,
|
||||
"decisionSuccessRate": 0.1362,
|
||||
"decisionTotal": 7092,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4433,
|
||||
"ambiguous_runtime": 4435,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -52022,15 +52021,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16120,
|
||||
"failureCount": 16122,
|
||||
"failureRate": 0.9435,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0565,
|
||||
"total": 17086,
|
||||
"unresolvedFailureCount": 9056
|
||||
"total": 17088,
|
||||
"unresolvedFailureCount": 9058
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -52059,6 +52058,7 @@
|
||||
"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。",
|
||||
@@ -52083,11 +52083,10 @@
|
||||
"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 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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17307,
|
||||
"summarizedRecords": 17309,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user