PyTorchKR and XCENA host KV Cache meetup on LLM inference in Korea
Overview
PyTorchKR and XCENA co-hosted KVCache Meetup Korea 2026 on September 30, 2026, a session on LLM inference and KV Cache.
Speakers from XCENA, SK hynix, FuriosaAI and LMCache covered CXL memory expansion, GPU and HBM bottlenecks, request scheduling on FuriosaAI's RNGD, and LMCache MP Mode. XCENA presented Maru, its open-source KV Cache storage engine. The report comes from the PyTorch Blog.
Written by AI from the articles below · updated Nov 3, 5:18 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- PyTorch BlogOfficialPyTorchKR and XCENA hold KVCache Meetup Korea 2026 on LLM inference and KV Cache
AIPyTorchKR and XCENA co-hosted KVCache Meetup Korea on September 30, 2026, with speakers from XCENA, SK hynix, FuriosaAI, and LMCache. The talks covered CXL memory expansion, GPU and HBM bottlenecks, request scheduling on RNGD, and LMCache MP Mode. XCENA presented its open-source Maru KV Cache storage engine.
Heat Trend
Not enough continuous observations to show a trend yet.