state: generation 11659 (cycle)

This commit is contained in:
2026-09-21 19:42:15 +00:00
parent e64ccf5e13
commit 39f242f56c
8 changed files with 1988 additions and 1939 deletions

View File

@@ -2768,7 +2768,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T19:38:20.571817+00:00",
"generatedAt": "2026-09-21T19:42:01.285599+00:00",
"summary": {
"activeBlockCount": 139,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T19:40:59.296547+00:00",
"generatedAt": "2026-09-21T19:42:13.414170+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T19:40:59.296547+00:00",
"catalogUpdatedAt": "2026-09-21T19:42:13.414170+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T19:40:59.296547+00:00",
"generatedAt": "2026-09-21T19:42:13.414170+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6896,6 +6896,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T19:40:59.296547+00:00",
"taskTreeUpdatedAt": "2026-09-21T19:42:13.414170+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:38:20.494912+00:00",
"lastSyncTime": "2026-09-21T19:38:20.253843+00:00",
"generatedAt": "2026-09-21T19:42:01.208198+00:00",
"lastSyncTime": "2026-09-21T19:42:00.658395+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4012,7 +4012,7 @@
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"memory_capacity": 1,
@@ -4020,18 +4020,18 @@
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 63,
"failureRate": 0.7778,
"failureCount": 64,
"failureRate": 0.7805,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2222,
"successRate": 0.2195,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 81,
"unresolvedFailureCount": 24
"total": 82,
"unresolvedFailureCount": 25
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 7,
@@ -4401,10 +4401,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 107,
"ambiguous_runtime": 108,
"参数/模板问题": 3
},
"failureCount": 110,
"failureCount": 111,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4414,8 +4414,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 110,
"unresolvedFailureCount": 110
"total": 111,
"unresolvedFailureCount": 111
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 17,
@@ -5523,7 +5523,7 @@
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"memory_capacity": 1,
@@ -5531,15 +5531,15 @@
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 63,
"failureRate": 0.7778,
"failureCount": 64,
"failureRate": 0.7805,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2222,
"total": 81,
"unresolvedFailureCount": 24
"successRate": 0.2195,
"total": 82,
"unresolvedFailureCount": 25
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 123,
@@ -5547,7 +5547,7 @@
"decisionSuccessRate": 0.0391,
"decisionTotal": 128,
"failureBreakdown": {
"ambiguous_runtime": 193,
"ambiguous_runtime": 194,
"backend_operator": 8,
"framework_architecture_unsupported": 23,
"memory_capacity": 7,
@@ -5556,15 +5556,15 @@
"tokenizer_compatibility": 82,
"参数/模板问题": 13
},
"failureCount": 346,
"failureCount": 347,
"failureRate": 0.9858,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0142,
"total": 351,
"unresolvedFailureCount": 206
"total": 352,
"unresolvedFailureCount": 207
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 74,
@@ -5594,7 +5594,7 @@
"unresolvedFailureCount": 104
}
},
"generatedAt": "2026-09-21T19:38:20.482780+00:00",
"generatedAt": "2026-09-21T19:42:01.195902+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5762,7 +5762,7 @@
"decisionSuccessRate": 0.1672,
"decisionTotal": 891,
"failureBreakdown": {
"ambiguous_runtime": 619,
"ambiguous_runtime": 620,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
@@ -5777,15 +5777,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1887,
"failureRate": 0.9268,
"failureCount": 1888,
"failureRate": 0.9269,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0732,
"total": 2036,
"unresolvedFailureCount": 1124
"successRate": 0.0731,
"total": 2037,
"unresolvedFailureCount": 1125
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 967,
@@ -5824,7 +5824,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 184,
"ambiguous_runtime": 185,
"backend_operator": 1,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
@@ -5833,15 +5833,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 247,
"failureCount": 248,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 247,
"unresolvedFailureCount": 228
"total": 248,
"unresolvedFailureCount": 229
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -11627,9 +11627,11 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "cohere2",
"pendingCount": 0,
@@ -11637,11 +11639,11 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|deepseek_v4_dspark|none": {
"attributableFailureCount": 1,
@@ -13599,6 +13601,29 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|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_fix_tokenizer",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -29179,9 +29204,11 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "cohere2",
@@ -29190,11 +29217,11 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|deepseek_v4_dspark|none|33": {
"attributableFailureCount": 1,
@@ -31987,6 +32014,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|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_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -37402,15 +37453,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16375,
"totalRecords": 16569,
"terminalRecords": 16377,
"totalRecords": 16571,
"totals": {
"attributableFailureCount": 5908,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6854,
"failureBreakdown": {
"ambiguous_runtime": 4012,
"ambiguous_runtime": 4014,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
@@ -37426,31 +37477,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15429,
"failureCount": 15431,
"failureRate": 0.9422,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0578,
"total": 16375,
"unresolvedFailureCount": 8596
"total": 16377,
"unresolvedFailureCount": 8598
},
"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。",
@@ -37490,6 +37541,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16569,
"summarizedRecords": 16571,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff