Expert parallelism (EP) is a key technique for serving Mixture-of-Experts (MoE) models at high throughput. WideEP deployments (where EP spans many workers) maximize KV cache capacity, enabling…
Elastic Expert Parallelism in vLLM
calendar_today
May 14, 2026
person
Itay Alroy (NVIDIA), Yongji Wu (Sky Computing), Rui Qiao (Anyscale), Tyler Michael Smith (Red Hat), Moein Khazraee (NVIDIA), Omri Kahalon (NVIDIA), Tzu-Ling Kan (NVIDIA), Ron Tourgeman (NVIDIA)
domain
vllm