conftrace_

token drafting

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

semi-autoregressive generation (1) token generation (1) large language model (1) language model inference (1) speculative decoding (1) inference acceleration (1)

Papers

Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree AAAI 2025