FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving

arXiv:2611.07542 · cs.AI · Submitted 2026-11-05 · Read on arXiv

cs.AI

Submitted: 2026-11-05

Updated: 2026-11-05

Code: https://github.com/vllm-project/vllm-ascend

Terminology

Sources

Related papers