ResearchDatasetsHeld-out datasetsHeld-out datasetsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLarge Language Model InferenceHeld-out datasets chatbot_instruction_prompts and finance-alpaca (test)265.7Throughput (TPS)14
Large Language Model InferenceHeld-out datasets chatbot_instruction_prompts and finance-alpaca (test)265.7Throughput (TPS)14