most citedAsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.DCShow all

2 papers · 1 filter

cs.DC2026

MoE-CORE: Coordinated Expert Offloading and Residency for Memory-Constrained MoE Inference

Ke Yang, Yongji Gao, Xushi Li +15

Sparse expert activation reduces MoE models' computation, yet expert weights can exceed limited device memory. Offloading makes inference feasible on a compact AI appliance but exp…

cs.DC2026

VPP: Virtual Pipeline Parallelism for Efficient Chunked Prefill in Long-Context LLM Inference

Yan Shi, Xiaochao Wang, Jingchun Gao +7

Chunked prefill pipeline parallelism (CPP) is a key technique for LLM inference. However, equal-size chunks exhibit imbalanced latency, as later chunks attend longer prefix KV cach…