state: generation 18681 (cycle)
This commit is contained in:
@@ -3320,7 +3320,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-30T05:26:32.906281+00:00",
|
||||
"generatedAt": "2026-09-30T05:40:14.722240+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 167,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-30T05:36:15.259237+00:00",
|
||||
"generatedAt": "2026-09-30T05:42:08.564505+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-30T05:36:15.259237+00:00",
|
||||
"catalogUpdatedAt": "2026-09-30T05:42:08.564505+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-30T05:36:15.259237+00:00",
|
||||
"generatedAt": "2026-09-30T05:42:08.564505+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6337,6 +6337,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-30T05:36:15.259237+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-30T05:42:08.564505+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-30T05:26:32.819601+00:00",
|
||||
"lastSyncTime": "2026-09-30T05:26:32.559197+00:00",
|
||||
"generatedAt": "2026-09-30T05:40:14.634982+00:00",
|
||||
"lastSyncTime": "2026-09-30T05:40:14.269914+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3448,24 +3448,24 @@
|
||||
"decisionSuccessRate": 0.0976,
|
||||
"decisionTotal": 41,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 67,
|
||||
"ambiguous_runtime": 69,
|
||||
"context_length": 6,
|
||||
"framework_architecture_unsupported": 30,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 112,
|
||||
"failureRate": 0.9655,
|
||||
"failureCount": 114,
|
||||
"failureRate": 0.9661,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0345,
|
||||
"successRate": 0.0339,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 116,
|
||||
"unresolvedFailureCount": 75
|
||||
"total": 118,
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 69,
|
||||
@@ -3905,25 +3905,25 @@
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 43,
|
||||
"ambiguous_runtime": 44,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 64,
|
||||
"failureRate": 0.8889,
|
||||
"failureCount": 65,
|
||||
"failureRate": 0.8904,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1111,
|
||||
"successRate": 0.1096,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 72,
|
||||
"unresolvedFailureCount": 47
|
||||
"total": 73,
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -6075,7 +6075,7 @@
|
||||
"decisionSuccessRate": 0.4118,
|
||||
"decisionTotal": 51,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 92,
|
||||
"ambiguous_runtime": 93,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"model_load": 5,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -6083,15 +6083,15 @@
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 130,
|
||||
"failureRate": 0.8609,
|
||||
"failureCount": 131,
|
||||
"failureRate": 0.8618,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 21,
|
||||
"successRate": 0.1391,
|
||||
"total": 151,
|
||||
"unresolvedFailureCount": 99
|
||||
"successRate": 0.1382,
|
||||
"total": 152,
|
||||
"unresolvedFailureCount": 100
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 57,
|
||||
@@ -6171,7 +6171,7 @@
|
||||
"decisionSuccessRate": 0.069,
|
||||
"decisionTotal": 145,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 179,
|
||||
"ambiguous_runtime": 181,
|
||||
"backend_operator": 15,
|
||||
"context_length": 6,
|
||||
"framework_architecture_unsupported": 81,
|
||||
@@ -6183,18 +6183,18 @@
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 345,
|
||||
"failureRate": 0.9718,
|
||||
"failureCount": 347,
|
||||
"failureRate": 0.972,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0282,
|
||||
"total": 355,
|
||||
"unresolvedFailureCount": 208
|
||||
"successRate": 0.028,
|
||||
"total": 357,
|
||||
"unresolvedFailureCount": 210
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-30T05:26:32.805905+00:00",
|
||||
"generatedAt": "2026-09-30T05:40:14.622103+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 107,
|
||||
@@ -6202,7 +6202,7 @@
|
||||
"decisionSuccessRate": 0.1705,
|
||||
"decisionTotal": 129,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 135,
|
||||
"ambiguous_runtime": 137,
|
||||
"context_length": 6,
|
||||
"framework_architecture_unsupported": 95,
|
||||
"memory_capacity": 2,
|
||||
@@ -6212,15 +6212,15 @@
|
||||
"日志缺失": 3,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 311,
|
||||
"failureRate": 0.9339,
|
||||
"failureCount": 313,
|
||||
"failureRate": 0.9343,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 22,
|
||||
"successRate": 0.0661,
|
||||
"total": 333,
|
||||
"unresolvedFailureCount": 204
|
||||
"successRate": 0.0657,
|
||||
"total": 335,
|
||||
"unresolvedFailureCount": 206
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 325,
|
||||
@@ -6286,7 +6286,7 @@
|
||||
"decisionSuccessRate": 0.0888,
|
||||
"decisionTotal": 822,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 508,
|
||||
"ambiguous_runtime": 509,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 302,
|
||||
@@ -6299,15 +6299,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1615,
|
||||
"failureCount": 1616,
|
||||
"failureRate": 0.9568,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0432,
|
||||
"total": 1688,
|
||||
"unresolvedFailureCount": 850
|
||||
"total": 1689,
|
||||
"unresolvedFailureCount": 851
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -7100,9 +7100,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5
|
||||
"ambiguous_runtime": 7
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "phi3",
|
||||
@@ -7114,8 +7114,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -11510,6 +11510,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -28278,9 +28301,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
@@ -28293,8 +28316,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -28302,9 +28325,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -28317,8 +28340,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -35213,6 +35236,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -53390,15 +53437,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17144,
|
||||
"totalRecords": 17365,
|
||||
"terminalRecords": 17147,
|
||||
"totalRecords": 17368,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6144,
|
||||
"decisionFailureRate": 0.8634,
|
||||
"decisionSuccessRate": 0.1366,
|
||||
"decisionTotal": 7116,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4463,
|
||||
"ambiguous_runtime": 4466,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -53414,15 +53461,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16172,
|
||||
"failureCount": 16175,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 942,
|
||||
"successCount": 972,
|
||||
"successRate": 0.0567,
|
||||
"total": 17144,
|
||||
"unresolvedFailureCount": 9086
|
||||
"total": 17147,
|
||||
"unresolvedFailureCount": 9089
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -53451,6 +53498,7 @@
|
||||
"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 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。",
|
||||
"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 Kunlunxin_p-800|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 MetaX_c-500|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 Ascend_910-b4|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 Cambricon_mlu-370-x4|vllm-customized|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -53476,11 +53524,10 @@
|
||||
"组合 hygon_k100-ai|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 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 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 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 Kunlunxin_p-800|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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17365,
|
||||
"summarizedRecords": 17368,
|
||||
"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