Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding Jan 30, 2024 • 9
RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation Paper • 2408.02545 • Published Aug 5, 2024 • 35
Accelerating Speculative Decoding using Dynamic Speculation Length Paper • 2405.04304 • Published May 7, 2024 • 2
Distributed Speculative Inference of Large Language Models Paper • 2405.14105 • Published May 23, 2024 • 16