ResearchDatasetsVILAVILAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsVisual-Language Model InferenceVILA Jetson Orin35.6Throughput (tokens/sec)4Visual-Language Model InferenceVILA A100155.3Throughput (tokens/sec)4Visual-Language Model InferenceVILA RTX 4090168.1Throughput (tokens/sec)3