Sep 05, 2024 [Blog with Together.ai] Speculative decoding for high-throughput long-context inference Aug 23, 2024 [Blog with Infini AI Lab] MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding May 21, 2024 Reshaping Bonsai May 20, 2024 Visual Prompt Tuning