ResearchTasksLLM Serving LatencyFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedANNS Workload 2.0 QPS, 30x delaysvLLM-NS0.72P50 Latency13Jul 9, 2026Crawler Workload 4.0 QPS, 10x delaysvLLM-NS0.64P50 Latency Score13Jul 9, 2026