state: generation 11587 (cycle)

This commit is contained in:
2026-09-21 17:41:30 +00:00
parent 47a1ff208c
commit 379b60bcaf
9 changed files with 1964 additions and 1896 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T17:23:43.184358+00:00",
"lastSyncTime": "2026-09-21T17:23:43.090457+00:00",
"generatedAt": "2026-09-21T17:41:29.155215+00:00",
"lastSyncTime": "2026-09-21T17:41:26.757156+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3060,13 +3060,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 23,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 22,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 6
},
"failureCount": 67,
"failureCount": 68,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -3076,8 +3076,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 43
"total": 68,
"unresolvedFailureCount": 44
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 201,
@@ -3995,7 +3995,7 @@
"decisionSuccessRate": 0.3214,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"backend_operator": 5,
"framework_architecture_unsupported": 17,
"memory_capacity": 1,
@@ -4003,18 +4003,18 @@
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 61,
"failureRate": 0.7722,
"failureCount": 62,
"failureRate": 0.775,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2278,
"successRate": 0.225,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 79,
"unresolvedFailureCount": 23
"total": 80,
"unresolvedFailureCount": 24
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 7,
@@ -4088,7 +4088,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 572,
"failureBreakdown": {
"ambiguous_runtime": 209,
"ambiguous_runtime": 210,
"architecture_compatibility": 14,
"backend_operator": 6,
"context_length": 29,
@@ -4100,7 +4100,7 @@
"runtime_memory": 3,
"tokenizer_compatibility": 46
},
"failureCount": 796,
"failureCount": 797,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -4110,8 +4110,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 796,
"unresolvedFailureCount": 209
"total": 797,
"unresolvedFailureCount": 210
},
"Iluvatar_bi-150|vllm|unknown": {
"attributableFailureCount": 1,
@@ -5409,7 +5409,7 @@
"decisionSuccessRate": 0.0243,
"decisionTotal": 3623,
"failureBreakdown": {
"ambiguous_runtime": 1491,
"ambiguous_runtime": 1492,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5423,15 +5423,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 45
},
"failureCount": 5936,
"failureCount": 5937,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6024,
"unresolvedFailureCount": 1536
"total": 6025,
"unresolvedFailureCount": 1537
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5506,7 +5506,7 @@
"decisionSuccessRate": 0.3214,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"backend_operator": 5,
"framework_architecture_unsupported": 17,
"memory_capacity": 1,
@@ -5514,15 +5514,15 @@
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 61,
"failureRate": 0.7722,
"failureCount": 62,
"failureRate": 0.775,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2278,
"total": 79,
"unresolvedFailureCount": 23
"successRate": 0.225,
"total": 80,
"unresolvedFailureCount": 24
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 123,
@@ -5555,7 +5555,7 @@
"decisionSuccessRate": 0.0267,
"decisionTotal": 75,
"failureBreakdown": {
"ambiguous_runtime": 69,
"ambiguous_runtime": 70,
"backend_operator": 1,
"context_length": 3,
"framework_architecture_unsupported": 62,
@@ -5566,18 +5566,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 27
},
"failureCount": 170,
"failureCount": 171,
"failureRate": 0.9884,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0116,
"total": 172,
"unresolvedFailureCount": 96
"total": 173,
"unresolvedFailureCount": 97
}
},
"generatedAt": "2026-09-21T17:23:43.137195+00:00",
"generatedAt": "2026-09-21T17:41:29.141921+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5611,7 +5611,7 @@
"decisionSuccessRate": 0.1654,
"decisionTotal": 381,
"failureBreakdown": {
"ambiguous_runtime": 169,
"ambiguous_runtime": 170,
"context_length": 1,
"framework_architecture_unsupported": 176,
"memory_capacity": 18,
@@ -5623,15 +5623,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 946,
"failureCount": 947,
"failureRate": 0.9376,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0624,
"total": 1009,
"unresolvedFailureCount": 626
"total": 1010,
"unresolvedFailureCount": 627
},
"Biren_166m": {
"attributableFailureCount": 184,
@@ -5745,7 +5745,7 @@
"decisionSuccessRate": 0.1676,
"decisionTotal": 889,
"failureBreakdown": {
"ambiguous_runtime": 617,
"ambiguous_runtime": 619,
"architecture_compatibility": 15,
"backend_operator": 11,
"context_length": 29,
@@ -5760,15 +5760,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1883,
"failureCount": 1885,
"failureRate": 0.9267,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0733,
"total": 2032,
"unresolvedFailureCount": 1122
"total": 2034,
"unresolvedFailureCount": 1124
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 967,
@@ -7189,9 +7189,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -7203,8 +7203,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -11907,10 +11907,10 @@
"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_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
@@ -11922,8 +11922,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none": {
"attributableFailureCount": 0,
@@ -12662,6 +12662,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation|mpt|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -17187,21 +17210,20 @@
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 1,
"framework_architecture_unsupported": 6,
"memory_capacity": 1,
"model_load": 1,
"参数/模板问题": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
@@ -17213,7 +17235,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 7
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -17276,13 +17298,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T13:30:42.156020+00:00",
"lastTerminalAt": "2026-09-21T17:41:26.757140+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -17290,8 +17313,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 0,
@@ -19884,31 +19907,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nemotron_h|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastTerminalAt": "2026-09-20T12:01:00.671259+00:00",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -20585,6 +20583,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation|mpt|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": "2026-09-21T17:41:26.757140+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation|qwen3_vl|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -22630,6 +22653,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -29190,9 +29237,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
@@ -29205,8 +29252,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
@@ -30286,6 +30333,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation|mpt|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": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -36486,15 +36557,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16342,
"totalRecords": 16536,
"terminalRecords": 16345,
"totalRecords": 16539,
"totals": {
"attributableFailureCount": 5900,
"decisionFailureRate": 0.8618,
"decisionSuccessRate": 0.1382,
"decisionTotal": 6846,
"failureBreakdown": {
"ambiguous_runtime": 3988,
"ambiguous_runtime": 3991,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
@@ -36510,31 +36581,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15396,
"failureCount": 15399,
"failureRate": 0.9421,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0579,
"total": 16342,
"unresolvedFailureCount": 8571
"total": 16345,
"unresolvedFailureCount": 8574
},
"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。",
@@ -36574,6 +36645,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16536,
"summarizedRecords": 16539,
"version": 1
}