inference/research
verifiedhigh · 0.95updated 2026-10-03

vLLM automatic prefix caching docs

repo

Fields

id
sources/engine-vllm-prefix-caching
URL
https://docs.vllm.ai/en/latest/features/automatic_prefix_caching/
Publisher
vLLM
Kind
repo
Accessed
2026-10-03
notes
vLLM APC docs. Defines what automatic prefix caching does and its limits (prefill-only, no decode gain).

Notes

vLLM APC docs. Defines what automatic prefix caching does and its limits (prefill-only, no decode gain).

Cross-references

This record references no other records.