state: generation 21915 (cycle)
This commit is contained in:
@@ -2777,7 +2777,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T16:13:00.136169+00:00",
|
||||
"generatedAt": "2026-10-07T16:20:51.452825+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 140,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-07T16:19:48.051256+00:00",
|
||||
"generatedAt": "2026-10-07T16:21:59.017546+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-07T16:19:48.051256+00:00",
|
||||
"catalogUpdatedAt": "2026-10-07T16:21:59.017546+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-07T16:19:48.051256+00:00",
|
||||
"generatedAt": "2026-10-07T16:21:59.017546+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6971,6 +6971,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-07T16:19:48.051256+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-07T16:21:59.017546+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-07T16:13:00.043287+00:00",
|
||||
"lastSyncTime": "2026-10-07T16:12:59.741980+00:00",
|
||||
"generatedAt": "2026-10-07T16:20:51.359635+00:00",
|
||||
"lastSyncTime": "2026-10-07T16:20:51.065423+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3366,25 +3366,25 @@
|
||||
"decisionSuccessRate": 0.2571,
|
||||
"decisionTotal": 35,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 48,
|
||||
"ambiguous_runtime": 49,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"model_load": 4,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.8977,
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.8989,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 9,
|
||||
"successRate": 0.1023,
|
||||
"successRate": 0.1011,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 88,
|
||||
"unresolvedFailureCount": 52
|
||||
"total": 89,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -5562,7 +5562,7 @@
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 66,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 102,
|
||||
"ambiguous_runtime": 103,
|
||||
"framework_architecture_unsupported": 36,
|
||||
"model_load": 7,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -5570,15 +5570,15 @@
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 154,
|
||||
"failureRate": 0.875,
|
||||
"failureCount": 155,
|
||||
"failureRate": 0.8757,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.125,
|
||||
"total": 176,
|
||||
"unresolvedFailureCount": 109
|
||||
"successRate": 0.1243,
|
||||
"total": 177,
|
||||
"unresolvedFailureCount": 110
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 65,
|
||||
@@ -5681,7 +5681,7 @@
|
||||
"unresolvedFailureCount": 257
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T16:12:59.974916+00:00",
|
||||
"generatedAt": "2026-10-07T16:20:51.341956+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 119,
|
||||
@@ -5774,7 +5774,7 @@
|
||||
"decisionSuccessRate": 0.0888,
|
||||
"decisionTotal": 833,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 513,
|
||||
"ambiguous_runtime": 514,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 311,
|
||||
@@ -5787,15 +5787,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1630,
|
||||
"failureCount": 1631,
|
||||
"failureRate": 0.9566,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 74,
|
||||
"successRate": 0.0434,
|
||||
"total": 1704,
|
||||
"unresolvedFailureCount": 855
|
||||
"total": 1705,
|
||||
"unresolvedFailureCount": 856
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 64,
|
||||
@@ -11096,9 +11096,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "lfm2",
|
||||
@@ -11110,8 +11110,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -37119,6 +37119,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "lfm2",
|
||||
"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|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -58350,15 +58374,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17411,
|
||||
"totalRecords": 17668,
|
||||
"terminalRecords": 17412,
|
||||
"totalRecords": 17669,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6249,
|
||||
"decisionFailureRate": 0.8647,
|
||||
"decisionSuccessRate": 0.1353,
|
||||
"decisionTotal": 7227,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4571,
|
||||
"ambiguous_runtime": 4572,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 129,
|
||||
@@ -58374,15 +58398,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16433,
|
||||
"failureCount": 16434,
|
||||
"failureRate": 0.9438,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 952,
|
||||
"successCount": 978,
|
||||
"successRate": 0.0562,
|
||||
"total": 17411,
|
||||
"unresolvedFailureCount": 9232
|
||||
"total": 17412,
|
||||
"unresolvedFailureCount": 9233
|
||||
},
|
||||
"warnings": [
|
||||
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -58391,14 +58415,14 @@
|
||||
"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 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。",
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -58443,6 +58467,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17668,
|
||||
"summarizedRecords": 17669,
|
||||
"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