FlashDecoding++: Faster Large Language Model Inference on GPUs Paper • 2311.01282 • Published Nov 2, 2023 • 35
Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache Paper • 2401.02669 • Published Jan 5 • 14
Speculative Streaming: Fast LLM Inference without Auxiliary Models Paper • 2402.11131 • Published Feb 16 • 41
