conftrace_

online serving

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

recommendation model (1) stream management (1) high concurrency (1) large language model (1) graph neural network (1) tensor parallelism (1) chunk size (1) latency optimization (1) recommender system (1) pipeline parallelism (1)

Papers

Revisiting Pipeline Parallelism for LLM Serving OSDI 2026 RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving COLING 2025