{"version":"1.0","type":"link","title":"Speculative decoding - Newikis","description":"Speculative decoding is an inference-time optimization for autoregressive large language models (LLMs) that generates multiple tokens per decoding step instead of one. A smaller draft model proposes a sequence of candidate tokens, and the larger target model verifies them in a single forward pass…","provider_name":"Newikis","provider_url":"https://newikis.com","cache_age":86400}