state: generation 11382 (cycle)
This commit is contained in:
@@ -2652,7 +2652,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T09:58:03.060909+00:00",
|
||||
"generatedAt": "2026-09-21T10:01:40.238300+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 133,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T10:00:34.891501+00:00",
|
||||
"generatedAt": "2026-09-21T10:01:48.565688+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T10:00:34.891501+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T10:01:48.565688+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T10:00:34.891501+00:00",
|
||||
"generatedAt": "2026-09-21T10:01:48.565688+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6520,6 +6520,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T10:00:34.891501+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T10:01:48.565688+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T09:54:22.094559+00:00",
|
||||
"lastSyncTime": "2026-09-21T09:54:21.980346+00:00",
|
||||
"generatedAt": "2026-09-21T10:01:40.168106+00:00",
|
||||
"lastSyncTime": "2026-09-21T10:01:37.498157+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2956,16 +2956,16 @@
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 20,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 20,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 29,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"ambiguous_runtime": 30,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 50,
|
||||
"failureCount": 52,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2975,8 +2975,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 50,
|
||||
"unresolvedFailureCount": 29
|
||||
"total": 52,
|
||||
"unresolvedFailureCount": 30
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 201,
|
||||
@@ -5441,32 +5441,32 @@
|
||||
"unresolvedFailureCount": 158
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 60,
|
||||
"decisionFailureRate": 0.9677,
|
||||
"decisionSuccessRate": 0.0323,
|
||||
"decisionTotal": 62,
|
||||
"attributableFailureCount": 61,
|
||||
"decisionFailureRate": 0.9683,
|
||||
"decisionSuccessRate": 0.0317,
|
||||
"decisionTotal": 63,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 51,
|
||||
"ambiguous_runtime": 52,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 55,
|
||||
"framework_architecture_unsupported": 56,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 19
|
||||
},
|
||||
"failureCount": 131,
|
||||
"failureRate": 0.985,
|
||||
"failureCount": 133,
|
||||
"failureRate": 0.9852,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.015,
|
||||
"total": 133,
|
||||
"unresolvedFailureCount": 70
|
||||
"successRate": 0.0148,
|
||||
"total": 135,
|
||||
"unresolvedFailureCount": 71
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T09:54:22.083548+00:00",
|
||||
"generatedAt": "2026-09-21T10:01:40.113915+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 91,
|
||||
@@ -5495,14 +5495,14 @@
|
||||
"unresolvedFailureCount": 149
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 315,
|
||||
"decisionFailureRate": 0.8355,
|
||||
"decisionSuccessRate": 0.1645,
|
||||
"decisionTotal": 377,
|
||||
"attributableFailureCount": 316,
|
||||
"decisionFailureRate": 0.836,
|
||||
"decisionSuccessRate": 0.164,
|
||||
"decisionTotal": 378,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 161,
|
||||
"ambiguous_runtime": 162,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 174,
|
||||
"framework_architecture_unsupported": 175,
|
||||
"memory_capacity": 18,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -5512,15 +5512,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 929,
|
||||
"failureRate": 0.9374,
|
||||
"failureCount": 931,
|
||||
"failureRate": 0.9376,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 62,
|
||||
"successRate": 0.0626,
|
||||
"total": 991,
|
||||
"unresolvedFailureCount": 612
|
||||
"successRate": 0.0624,
|
||||
"total": 993,
|
||||
"unresolvedFailureCount": 613
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 182,
|
||||
@@ -7008,9 +7008,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "phi3",
|
||||
@@ -7022,8 +7022,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7278,6 +7278,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|zaya|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "zaya",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -21366,6 +21389,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "phi3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -21702,6 +21749,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|zaya|none|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "zaya",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -33399,20 +33470,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16206,
|
||||
"totalRecords": 16389,
|
||||
"terminalRecords": 16208,
|
||||
"totalRecords": 16391,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5863,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6806,
|
||||
"attributableFailureCount": 5864,
|
||||
"decisionFailureRate": 0.8615,
|
||||
"decisionSuccessRate": 0.1385,
|
||||
"decisionTotal": 6807,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3909,
|
||||
"ambiguous_runtime": 3910,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 319,
|
||||
"framework_architecture_unsupported": 2058,
|
||||
"framework_architecture_unsupported": 2059,
|
||||
"memory_capacity": 1197,
|
||||
"model_load": 495,
|
||||
"platform_infrastructure": 924,
|
||||
@@ -33423,31 +33494,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15263,
|
||||
"failureCount": 15265,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 924,
|
||||
"successCount": 943,
|
||||
"successRate": 0.0582,
|
||||
"total": 16206,
|
||||
"unresolvedFailureCount": 8476
|
||||
"total": 16208,
|
||||
"unresolvedFailureCount": 8477
|
||||
},
|
||||
"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。",
|
||||
@@ -33487,6 +33558,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16389,
|
||||
"summarizedRecords": 16391,
|
||||
"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