Showing 2026Show all
2 papers · 1 filter
cs.DC2026
WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse
Aaryam Sharma
Pipeline parallelism can improve prefill throughput by processing multiple request chunks concurrently across different stages of the model. However, keeping the pipeline fully uti…
cs.LG2026
When Is a Draft Accepted? A Theory of Acceptance in Speculative Decoding
Aaryam Sharma
Speculative decoding accelerates language model inference by using a fast drafter to propose candidate tokens that are then verified by a larger target model. Existing theory large…