Data Conference Databasea Query.Farm index
Speakers

Junchen Jiang

Employers on the program

  1. 2025University of Chicago1 talk
Events1
Conferences1
Talks1
Years active2025

Appearances by year

201920202021202220232024202520262027
  • PyTorch Conference

Talks

DateEventConferenceRoleTitleLinks
Oct 22, 2025PyTorch Conference 2025PyTorch ConferencespeakerScaling KV Caches for LLMs: How LMCache + NIXL Handle Network and Storage Heterogeneity
as University of Chicago
Efficient KV cache management is critical for scalable, low-latency LLM inference. LMCache, a widely adopted open-source KV caching layer used in vLLM…Show less

Efficient KV cache management is critical for scalable, low-latency LLM inference. LMCache, a widely adopted open-source KV caching layer used in vLLM deployments, addresses two fundamental challenges: (1) transferring KV caches across LLM instances, and (2) storing KV caches into diverse backend...

Frequent co-speakers

SpeakerShared eventsShared talksLast together
Moein Khazraee112025

Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.