state: generation 11656 (cycle)
This commit is contained in:
@@ -2768,7 +2768,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T19:35:31.660543+00:00",
|
||||
"generatedAt": "2026-09-21T19:38:20.571817+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 139,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T19:37:18.681217+00:00",
|
||||
"generatedAt": "2026-09-21T19:38:31.254404+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T19:37:18.681217+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T19:38:31.254404+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T19:37:18.681217+00:00",
|
||||
"generatedAt": "2026-09-21T19:38:31.254404+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6896,6 +6896,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T19:37:18.681217+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T19:38:31.254404+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T19:21:35.669232+00:00",
|
||||
"lastSyncTime": "2026-09-21T19:21:35.063209+00:00",
|
||||
"generatedAt": "2026-09-21T19:38:20.494912+00:00",
|
||||
"lastSyncTime": "2026-09-21T19:38:20.253843+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4401,10 +4401,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 106,
|
||||
"ambiguous_runtime": 107,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 109,
|
||||
"failureCount": 110,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -4414,8 +4414,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 109,
|
||||
"unresolvedFailureCount": 109
|
||||
"total": 110,
|
||||
"unresolvedFailureCount": 110
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -5547,7 +5547,7 @@
|
||||
"decisionSuccessRate": 0.0391,
|
||||
"decisionTotal": 128,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 192,
|
||||
"ambiguous_runtime": 193,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 7,
|
||||
@@ -5556,15 +5556,15 @@
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 345,
|
||||
"failureRate": 0.9857,
|
||||
"failureCount": 346,
|
||||
"failureRate": 0.9858,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 17,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0143,
|
||||
"total": 350,
|
||||
"unresolvedFailureCount": 205
|
||||
"successRate": 0.0142,
|
||||
"total": 351,
|
||||
"unresolvedFailureCount": 206
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 74,
|
||||
@@ -5594,7 +5594,7 @@
|
||||
"unresolvedFailureCount": 104
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T19:21:35.657452+00:00",
|
||||
"generatedAt": "2026-09-21T19:38:20.482780+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5824,7 +5824,7 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 183,
|
||||
"ambiguous_runtime": 184,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"memory_capacity": 1,
|
||||
@@ -5833,15 +5833,15 @@
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 246,
|
||||
"failureCount": 247,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 246,
|
||||
"unresolvedFailureCount": 227
|
||||
"total": 247,
|
||||
"unresolvedFailureCount": 228
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -14313,6 +14313,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|smollm3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "smollm3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -33261,6 +33284,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|smollm3|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "smollm3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -37355,15 +37402,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16374,
|
||||
"totalRecords": 16568,
|
||||
"terminalRecords": 16375,
|
||||
"totalRecords": 16569,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5908,
|
||||
"decisionFailureRate": 0.862,
|
||||
"decisionSuccessRate": 0.138,
|
||||
"decisionTotal": 6854,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4011,
|
||||
"ambiguous_runtime": 4012,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 104,
|
||||
@@ -37379,31 +37426,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15428,
|
||||
"failureCount": 15429,
|
||||
"failureRate": 0.9422,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 946,
|
||||
"successRate": 0.0578,
|
||||
"total": 16374,
|
||||
"unresolvedFailureCount": 8595
|
||||
"total": 16375,
|
||||
"unresolvedFailureCount": 8596
|
||||
},
|
||||
"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 Vastai_va16 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。",
|
||||
"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。",
|
||||
@@ -37443,6 +37490,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16568,
|
||||
"summarizedRecords": 16569,
|
||||
"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