{"id":"2610.02800","title":"BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration","url":"https://codeofpaper.com/paper/2610.02800","arxiv_url":"https://arxiv.org/abs/2610.02800","published":"2026-10-02","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}