2 papers
cs.CL2025
Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
Nadav Timor, Jonathan Mamou, Daniel Korat +5
Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generat…
cs.CL2025
Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs
Ravi Ghadia, Avinash Kumar, Gaurav Jain +2
Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consump…