Spotlight
in
Workshop: ML for Systems Sat, Dec 6, 2025 • 4:05 PM – 4:15 PM PST

Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference (Spotlight Paper)

Abstract

Spotlight: Ruokai Yin (Yale) Learning to Shard: RL for Co-optimizing the Parallelism Degrees and Per-operator Sharding Dimensions in Distributed LLM Inference

Video

Chat is not available.