state: generation 17715 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T03:49:01.552052+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.258601+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"generatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"catalogUpdatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"generatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6545,6 +6545,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-28T03:31:38.420170+00:00",
|
||||
"lastSyncTime": "2026-09-28T03:31:38.156601+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.173772+00:00",
|
||||
"lastSyncTime": "2026-09-28T03:58:09.851955+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3715,27 +3715,27 @@
|
||||
"unresolvedFailureCount": 108
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.7458,
|
||||
"decisionSuccessRate": 0.2542,
|
||||
"decisionTotal": 59,
|
||||
"attributableFailureCount": 45,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 60,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 13,
|
||||
"framework_architecture_unsupported": 31,
|
||||
"framework_architecture_unsupported": 32,
|
||||
"model_load": 11,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 57,
|
||||
"failureRate": 0.7917,
|
||||
"failureCount": 58,
|
||||
"failureRate": 0.7945,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 15,
|
||||
"successRate": 0.2083,
|
||||
"successRate": 0.2055,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 72,
|
||||
"total": 73,
|
||||
"unresolvedFailureCount": 13
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -5957,17 +5957,17 @@
|
||||
"unresolvedFailureCount": 6473
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3623,
|
||||
"attributableFailureCount": 3624,
|
||||
"decisionFailureRate": 0.9739,
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3720,
|
||||
"decisionTotal": 3721,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1584,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1357,
|
||||
"framework_architecture_unsupported": 1358,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 220,
|
||||
"platform_infrastructure": 871,
|
||||
@@ -5976,14 +5976,14 @@
|
||||
"tokenizer_compatibility": 416,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6128,
|
||||
"failureCount": 6129,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 871,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6225,
|
||||
"total": 6226,
|
||||
"unresolvedFailureCount": 1634
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6134,7 +6134,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T03:31:38.406685+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.159678+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6191,15 +6191,15 @@
|
||||
"unresolvedFailureCount": 704
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 187,
|
||||
"decisionFailureRate": 0.8821,
|
||||
"decisionSuccessRate": 0.1179,
|
||||
"decisionTotal": 212,
|
||||
"attributableFailureCount": 188,
|
||||
"decisionFailureRate": 0.8826,
|
||||
"decisionSuccessRate": 0.1174,
|
||||
"decisionTotal": 213,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 251,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 120,
|
||||
"framework_architecture_unsupported": 121,
|
||||
"memory_capacity": 2,
|
||||
"model_load": 23,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -6210,14 +6210,14 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 743,
|
||||
"failureRate": 0.9674,
|
||||
"failureCount": 744,
|
||||
"failureRate": 0.9675,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0326,
|
||||
"total": 768,
|
||||
"successRate": 0.0325,
|
||||
"total": 769,
|
||||
"unresolvedFailureCount": 554
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -10414,6 +10414,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -32822,6 +32845,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -51479,20 +51526,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17068,
|
||||
"totalRecords": 17289,
|
||||
"terminalRecords": 17069,
|
||||
"totalRecords": 17290,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6116,
|
||||
"attributableFailureCount": 6117,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7082,
|
||||
"decisionTotal": 7083,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4425,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2173,
|
||||
"framework_architecture_unsupported": 2174,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 550,
|
||||
"platform_infrastructure": 938,
|
||||
@@ -51503,14 +51550,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16102,
|
||||
"failureCount": 16103,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0566,
|
||||
"total": 17068,
|
||||
"total": 17069,
|
||||
"unresolvedFailureCount": 9048
|
||||
},
|
||||
"warnings": [
|
||||
@@ -51519,15 +51566,15 @@
|
||||
"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 MetaX_c-500 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 Vastai_va16 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 Ascend_910-b3 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 Biren_166m 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 Iluvatar_bi-100 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 Mthreads_s4000 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。",
|
||||
"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 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 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。",
|
||||
@@ -51551,6 +51598,7 @@
|
||||
"组合 Cambricon_mlu-370-x4|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|transformers|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm-patch-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 Vastai_va16|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 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 Mthreads_s4000|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_bi-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51564,11 +51612,10 @@
|
||||
"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 Mthreads_s4000|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_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 Iluvatar_bi-150|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 Vastai_va16|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 Iluvatar_bi-150|llamacpp|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": 17289,
|
||||
"summarizedRecords": 17290,
|
||||
"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