state: generation 11813 (cycle_no_slots)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T22:03:31.665503+00:00",
|
||||
"lastSyncTime": "2026-09-21T22:03:31.571348+00:00",
|
||||
"generatedAt": "2026-09-21T22:08:12.190998+00:00",
|
||||
"lastSyncTime": "2026-09-21T22:08:11.958925+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3287,9 +3287,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 40
|
||||
"ambiguous_runtime": 41
|
||||
},
|
||||
"failureCount": 40,
|
||||
"failureCount": 41,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -3299,8 +3299,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 40,
|
||||
"unresolvedFailureCount": 40
|
||||
"total": 41,
|
||||
"unresolvedFailureCount": 41
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 44,
|
||||
@@ -5632,7 +5632,7 @@
|
||||
"decisionSuccessRate": 0.0391,
|
||||
"decisionTotal": 128,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 199,
|
||||
"ambiguous_runtime": 200,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 7,
|
||||
@@ -5641,15 +5641,15 @@
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 352,
|
||||
"failureCount": 353,
|
||||
"failureRate": 0.986,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 17,
|
||||
"successCount": 5,
|
||||
"successRate": 0.014,
|
||||
"total": 357,
|
||||
"unresolvedFailureCount": 212
|
||||
"total": 358,
|
||||
"unresolvedFailureCount": 213
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 78,
|
||||
@@ -5679,7 +5679,7 @@
|
||||
"unresolvedFailureCount": 120
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T22:03:31.653393+00:00",
|
||||
"generatedAt": "2026-09-21T22:08:12.180281+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5741,7 +5741,7 @@
|
||||
"decisionSuccessRate": 0.1185,
|
||||
"decisionTotal": 211,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 181,
|
||||
"ambiguous_runtime": 182,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 120,
|
||||
@@ -5755,15 +5755,15 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 672,
|
||||
"failureRate": 0.9641,
|
||||
"failureCount": 673,
|
||||
"failureRate": 0.9642,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0359,
|
||||
"total": 697,
|
||||
"unresolvedFailureCount": 484
|
||||
"successRate": 0.0358,
|
||||
"total": 698,
|
||||
"unresolvedFailureCount": 485
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 717,
|
||||
@@ -8435,6 +8435,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|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_fix_tokenizer",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -17802,7 +17825,7 @@
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T20:34:21.547032+00:00",
|
||||
"lastTerminalAt": "2026-09-21T22:08:11.958925+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -18918,6 +18941,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T22:08:11.958925+00:00",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -21051,15 +21099,15 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 3
|
||||
"memory_capacity": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-20T12:21:49.901832+00:00",
|
||||
@@ -21072,7 +21120,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
|
||||
@@ -25093,6 +25141,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|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_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -38347,15 +38419,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16420,
|
||||
"totalRecords": 16614,
|
||||
"terminalRecords": 16421,
|
||||
"totalRecords": 16615,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5921,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6870,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4040,
|
||||
"ambiguous_runtime": 4041,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 105,
|
||||
@@ -38371,31 +38443,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15471,
|
||||
"failureCount": 15472,
|
||||
"failureRate": 0.9422,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 949,
|
||||
"successRate": 0.0578,
|
||||
"total": 16420,
|
||||
"unresolvedFailureCount": 8625
|
||||
"total": 16421,
|
||||
"unresolvedFailureCount": 8626
|
||||
},
|
||||
"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。",
|
||||
@@ -38435,6 +38507,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16614,
|
||||
"summarizedRecords": 16615,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user