Guanghao Li

Resource constraints often limit the parameter capacity of Large Language Models (LLMs), thereby hindering their performance. Although existing approaches leverage parameter sharing to reuse a fixed set of parameters within constrained budgets, they typically require each layer to fulfill multipl...

Autoregressive (AR) decoding in large language models (LLMs) is latency-bounded by strictly sequential token generation.Speculative decoding mitigates this bottleneck by letting a fast drafter propose multi-token candidates that are then verified in parallel by the target model; yet most existing...