A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Doc] Fix link to prefix caching design (#22384)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Yong Hoon Shin committed
Aug 7, 2025 at 00:28 UTC
5e8398805ed6b6e59e3408fe64ed37d189b77149
1 file changed
+1
-1
docs/features/automatic_prefix_caching.md
+1
-1
@@ -5,7 +5,7 @@
5
Automatic Prefix Caching (APC in short) caches the KV cache of existing queries, so that a new query can directly reuse the KV cache if it shares the same prefix with one of the existing queries, allowing the new query to skip the computation of the shared part.
6
7
!!! note
8
- Technical details on how vLLM implements APC can be found [here](../design/automatic_prefix_caching.md).
8
+ Technical details on how vLLM implements APC can be found [here](../design/prefix_caching.md).
9
10
## Enabling APC in vLLM
11