conftrace_

prefill-decoding disaggregation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model serving (1) latency optimization (1) gpu resource allocation (1) throughput optimization (1) model parallelism (1)

Papers

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024