conftrace_

large language model serving

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prefill-decoding disaggregation (1) prefill-decode disaggregation (1) workload generation (1) performance benchmarking (1) decentralized serving (1) communication privacy (1) inference instance (1) peer-to-peer network (1) workload characterization (1) gpu cluster (1)

Papers

Efficient LLM Serving on Commodity GPU Clusters with Data-Reduced Cross-Instance Orchestration OSDI 2026 PlanetServe: A Decentralized, Scalable, and Privacy-Preserving Overlay for Democratizing Large Language Model Serving NSDI 2026 ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production NSDI 2026 DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024