FlexGen:High-throughput Generative Inference of Large Language Models with a Single GPU - Ying Sheng
About this video
Editorial review · 85% confidenceNew channel uwsampl: title sample judged 'whole' (Nearly every upload is a technical research talk or tutorial session on compiler/ML systems topics, consistent with genu); passed a second screen for sellers/exam-prep/re-uploads; 2 of 3 sampled transcripts showed teaching, 0 not; every title checked strictly; oEmbed verified.
A 33-minute video from uwsampl: “FlexGen:High-throughput Generative Inference of Large Language Models with a Single GPU - Ying Sheng”.
Video by uwsampl, played through YouTube's embedded player.