EL-Attention: Memory Efficient Lossless Attention for Generation Paper • 2105.04779 • Published May 11, 2021
Speculative Streaming: Fast LLM Inference without Auxiliary Models Paper • 2402.11131 • Published Feb 16, 2024 • 43
Speculative Streaming: Fast LLM Inference without Auxiliary Models Paper • 2402.11131 • Published Feb 16, 2024 • 43