Amphista: Accelerate LLM Inference with Bi-directional Multiple Drafting Heads in a Non-autoregressive Style
Abstract: Large Language Models (LLMs) inherently use autoregressive decoding, which lacks parallelism in inference and results in significantly slow inference speeds, especially when hardware parallel accelerators and memory bandwidth are not fully utilized. In this work, we propose Amphista, a speculative decoding algorithm that adheres to a non-autoregressive decoding paradigm. Owing to the increased parallelism, our method demonstrates higher efficiency in inference compared to autoregressive methods. Specifically, Amphista models an Auto-embedding Block capable of parallel inference, incorporating bi-directional attention to enable interaction between different drafting heads. Additionally, Amphista implements Staged Adaptation Layers to facilitate the transition of semantic information from the base model's autoregressive inference to the drafting heads' non-autoregressive speculation, thereby achieving paradigm transformation and feature fusion. We conduct a series of experiments on a suite of Vicuna models using MT-Bench and Spec-Bench. For the Vicuna 33B model, Amphista achieves up to 2.75$\times$ and 1.40$\times$ wall-clock acceleration compared to vanilla autoregressive decoding and Medusa, respectively, while preserving lossless generation quality.
Paper Type: Long
Research Area: Generation
Research Area Keywords: efficient models, inference methods, model architectures
Contribution Types: Approaches to low-resource settings, Approaches low compute settings-efficiency
Languages Studied: English
Submission Number: 2096
Loading