state: generation 21544 (cycle)
This commit is contained in:
@@ -2777,7 +2777,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-06T20:31:24.959811+00:00",
|
||||
"generatedAt": "2026-10-06T20:38:38.421796+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 140,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-06T20:37:35.462804+00:00",
|
||||
"generatedAt": "2026-10-06T20:40:22.771043+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-06T20:37:35.462804+00:00",
|
||||
"catalogUpdatedAt": "2026-10-06T20:40:22.771043+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-06T20:37:35.462804+00:00",
|
||||
"generatedAt": "2026-10-06T20:40:22.771043+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6643,6 +6643,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-06T20:37:35.462804+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-06T20:40:22.771043+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-06T19:35:17.107434+00:00",
|
||||
"lastSyncTime": "2026-10-06T19:35:16.862376+00:00",
|
||||
"generatedAt": "2026-10-06T20:38:38.329289+00:00",
|
||||
"lastSyncTime": "2026-10-06T20:38:38.063592+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4658,10 +4658,10 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 632,
|
||||
"attributableFailureCount": 633,
|
||||
"decisionFailureRate": 0.9605,
|
||||
"decisionSuccessRate": 0.0395,
|
||||
"decisionTotal": 658,
|
||||
"decisionTotal": 659,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 133,
|
||||
"architecture_compatibility": 20,
|
||||
@@ -4669,24 +4669,24 @@
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 196,
|
||||
"memory_capacity": 84,
|
||||
"model_load": 64,
|
||||
"model_load": 65,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 98,
|
||||
"runtime_memory": 2,
|
||||
"tokenizer_compatibility": 79,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 777,
|
||||
"failureRate": 0.9676,
|
||||
"failureCount": 778,
|
||||
"failureRate": 0.9677,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 26,
|
||||
"successRate": 0.0324,
|
||||
"successRate": 0.0323,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 803,
|
||||
"total": 804,
|
||||
"unresolvedFailureCount": 142
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
@@ -5479,10 +5479,10 @@
|
||||
"unresolvedFailureCount": 6477
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3665,
|
||||
"decisionFailureRate": 0.9721,
|
||||
"decisionSuccessRate": 0.0279,
|
||||
"decisionTotal": 3770,
|
||||
"attributableFailureCount": 3666,
|
||||
"decisionFailureRate": 0.9722,
|
||||
"decisionSuccessRate": 0.0278,
|
||||
"decisionTotal": 3771,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1600,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -5491,21 +5491,21 @@
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1387,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 227,
|
||||
"model_load": 228,
|
||||
"platform_infrastructure": 879,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 66,
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6194,
|
||||
"failureCount": 6195,
|
||||
"failureRate": 0.9833,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 879,
|
||||
"successCount": 105,
|
||||
"successRate": 0.0167,
|
||||
"total": 6299,
|
||||
"total": 6300,
|
||||
"unresolvedFailureCount": 1650
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5656,7 +5656,7 @@
|
||||
"unresolvedFailureCount": 235
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-06T19:35:17.090433+00:00",
|
||||
"generatedAt": "2026-10-06T20:38:38.314877+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 119,
|
||||
@@ -5931,10 +5931,10 @@
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 667,
|
||||
"decisionFailureRate": 0.8194,
|
||||
"decisionSuccessRate": 0.1806,
|
||||
"decisionTotal": 814,
|
||||
"attributableFailureCount": 668,
|
||||
"decisionFailureRate": 0.8196,
|
||||
"decisionSuccessRate": 0.1804,
|
||||
"decisionTotal": 815,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 305,
|
||||
"architecture_compatibility": 21,
|
||||
@@ -5942,7 +5942,7 @@
|
||||
"context_length": 59,
|
||||
"framework_architecture_unsupported": 200,
|
||||
"memory_capacity": 85,
|
||||
"model_load": 64,
|
||||
"model_load": 65,
|
||||
"platform_infrastructure": 5,
|
||||
"repository_structure": 114,
|
||||
"runtime_memory": 2,
|
||||
@@ -5951,14 +5951,14 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1438,
|
||||
"failureCount": 1439,
|
||||
"failureRate": 0.9073,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 147,
|
||||
"successRate": 0.0927,
|
||||
"total": 1585,
|
||||
"total": 1586,
|
||||
"unresolvedFailureCount": 766
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -20699,6 +20699,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -51253,6 +51276,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|lfm2|none|30": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -57546,13 +57593,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17343,
|
||||
"totalRecords": 17567,
|
||||
"terminalRecords": 17344,
|
||||
"totalRecords": 17568,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6235,
|
||||
"attributableFailureCount": 6236,
|
||||
"decisionFailureRate": 0.8644,
|
||||
"decisionSuccessRate": 0.1356,
|
||||
"decisionTotal": 7213,
|
||||
"decisionTotal": 7214,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4550,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -57561,7 +57608,7 @@
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2259,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 567,
|
||||
"model_load": 568,
|
||||
"platform_infrastructure": 952,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
@@ -57570,14 +57617,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16365,
|
||||
"failureCount": 16366,
|
||||
"failureRate": 0.9436,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 952,
|
||||
"successCount": 978,
|
||||
"successRate": 0.0564,
|
||||
"total": 17343,
|
||||
"total": 17344,
|
||||
"unresolvedFailureCount": 9178
|
||||
},
|
||||
"warnings": [
|
||||
@@ -57587,14 +57634,14 @@
|
||||
"GPU hygon_k100-ai 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 Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"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 Kunlunxin_p-800 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 Sunrise_pt-200-x1 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 Cambricon_mlu-370-x4 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 Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -57638,6 +57685,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17567,
|
||||
"summarizedRecords": 17568,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user