# PyTorchKR and XCENA hold KVCache Meetup Korea 2026 on LLM inference and KV Cache

> Original title: KVCache Meetup Korea 2026: Event Recap

- Source: PyTorch Blog
- Published: 2026-11-03T09:22:03.000Z
- Bad Influence: https://badinfluence.news/items/qa7flvrgco7mlv75q5sl8a9r4
- Original: https://pytorch.org/blog/kvcache-meetup-korea-2026-event-recap/

## Summary

PyTorchKR 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.