state: generation 11421 (cycle)

This commit is contained in:
2026-09-21 11:35:14 +00:00
parent c31c558fe4
commit dce15c60d4
9 changed files with 2066 additions and 1972 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T11:16:32.135781+00:00",
"lastSyncTime": "2026-09-21T11:16:32.032065+00:00",
"generatedAt": "2026-09-21T11:35:05.656601+00:00",
"lastSyncTime": "2026-09-21T11:35:03.480283+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4227,27 +4227,27 @@
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 16,
"decisionFailureRate": 0.5517,
"decisionSuccessRate": 0.4483,
"decisionTotal": 29,
"attributableFailureCount": 17,
"decisionFailureRate": 0.5667,
"decisionSuccessRate": 0.4333,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 15,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 16,
"model_load": 1
},
"failureCount": 21,
"failureRate": 0.6176,
"failureCount": 23,
"failureRate": 0.6389,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.3824,
"successRate": 0.3611,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 5
"total": 36,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4962,20 +4962,21 @@
"failureBreakdown": {
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 10,
"model_load": 2
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 26,
"failureRate": 0.8387,
"failureCount": 30,
"failureRate": 0.8571,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.1613,
"successRate": 0.1429,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 31,
"unresolvedFailureCount": 14
"total": 35,
"unresolvedFailureCount": 18
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 430,
@@ -5318,17 +5319,17 @@
"unresolvedFailureCount": 6445
},
"vllm": {
"attributableFailureCount": 3527,
"attributableFailureCount": 3528,
"decisionFailureRate": 0.9762,
"decisionSuccessRate": 0.0238,
"decisionTotal": 3613,
"decisionTotal": 3614,
"failureBreakdown": {
"ambiguous_runtime": 1481,
"ambiguous_runtime": 1482,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1297,
"framework_architecture_unsupported": 1298,
"memory_capacity": 720,
"model_load": 207,
"platform_infrastructure": 865,
@@ -5337,15 +5338,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 41
},
"failureCount": 5914,
"failureCount": 5916,
"failureRate": 0.9857,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 86,
"successRate": 0.0143,
"total": 6000,
"unresolvedFailureCount": 1522
"total": 6002,
"unresolvedFailureCount": 1523
},
"vllm-customized": {
"attributableFailureCount": 4,
@@ -5451,17 +5452,17 @@
"model_load": 2,
"platform_infrastructure": 17,
"tokenizer_compatibility": 82,
"参数/模板问题": 9
"参数/模板问题": 13
},
"failureCount": 302,
"failureRate": 0.9837,
"failureCount": 306,
"failureRate": 0.9839,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0163,
"total": 307,
"unresolvedFailureCount": 164
"successRate": 0.0161,
"total": 311,
"unresolvedFailureCount": 168
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 67,
@@ -5490,7 +5491,7 @@
"unresolvedFailureCount": 86
}
},
"generatedAt": "2026-09-21T11:16:32.082238+00:00",
"generatedAt": "2026-09-21T11:35:05.645850+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 94,
@@ -5684,16 +5685,16 @@
"unresolvedFailureCount": 1122
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 966,
"decisionFailureRate": 0.8474,
"decisionSuccessRate": 0.1526,
"decisionTotal": 1140,
"attributableFailureCount": 967,
"decisionFailureRate": 0.8475,
"decisionSuccessRate": 0.1525,
"decisionTotal": 1141,
"failureBreakdown": {
"ambiguous_runtime": 345,
"ambiguous_runtime": 346,
"architecture_compatibility": 47,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 287,
"framework_architecture_unsupported": 288,
"memory_capacity": 219,
"model_load": 85,
"platform_infrastructure": 7,
@@ -5704,15 +5705,15 @@
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1687,
"failureRate": 0.9065,
"failureCount": 1689,
"failureRate": 0.9066,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 174,
"successRate": 0.0935,
"total": 1861,
"unresolvedFailureCount": 714
"successRate": 0.0934,
"total": 1863,
"unresolvedFailureCount": 715
},
"Kunlunxin_p-800": {
"attributableFailureCount": 15,
@@ -5858,19 +5859,19 @@
"platform_infrastructure": 14,
"repository_structure": 57,
"tokenizer_compatibility": 12,
"参数/模板问题": 238,
"参数/模板问题": 242,
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1764,
"failureRate": 0.9687,
"failureCount": 1768,
"failureRate": 0.9688,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 57,
"successRate": 0.0313,
"total": 1821,
"unresolvedFailureCount": 1306
"successRate": 0.0312,
"total": 1825,
"unresolvedFailureCount": 1310
},
"hygon_k100-ai": {
"attributableFailureCount": 699,
@@ -12162,6 +12163,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12370,14 +12394,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -12389,7 +12413,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3|none": {
@@ -16298,11 +16322,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"memory_capacity": 2
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -16314,7 +16337,32 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T11:35:03.480257+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -19592,10 +19640,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T11:30:54.600137+00:00",
@@ -19608,8 +19655,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
@@ -19711,6 +19758,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T11:35:03.480257+00:00",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -28867,6 +28939,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -29200,14 +29296,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|33": {
"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",
"loadSizeLog2Bucket": 33,
@@ -29220,7 +29316,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|34": {
@@ -34444,55 +34540,55 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16251,
"totalRecords": 16435,
"terminalRecords": 16257,
"totalRecords": 16441,
"totals": {
"attributableFailureCount": 5877,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6820,
"attributableFailureCount": 5878,
"decisionFailureRate": 0.8618,
"decisionSuccessRate": 0.1382,
"decisionTotal": 6821,
"failureBreakdown": {
"ambiguous_runtime": 3933,
"ambiguous_runtime": 3934,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 320,
"framework_architecture_unsupported": 2067,
"framework_architecture_unsupported": 2068,
"memory_capacity": 1197,
"model_load": 497,
"platform_infrastructure": 925,
"repository_structure": 736,
"runtime_memory": 85,
"tokenizer_compatibility": 660,
"参数/模板问题": 3180,
"参数/模板问题": 3184,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15308,
"failureCount": 15314,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 943,
"successRate": 0.058,
"total": 16251,
"unresolvedFailureCount": 8506
"total": 16257,
"unresolvedFailureCount": 8511
},
"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。",
@@ -34532,6 +34628,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16435,
"summarizedRecords": 16441,
"version": 1
}