biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Support clear mm and encoder cache (#33452)

Browse Source 
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
jma99_2333
2026-01-31 07:22:25 -08:00
committed by GitHub
parent 13b842f271
commit 22d9a056d5
15 changed files with 212 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/usage/security.md
View File

@@ -172,6 +172,7 @@ These endpoints are **only available when the environment variable `VLLM_SERVER_
- `/server_info` - Get detailed server configuration
- `/reset_prefix_cache` - Reset prefix cache (can disrupt service)
- `/reset_mm_cache` - Reset multimodal cache (can disrupt service)
- `/reset_encoder_cache` - Reset encoder cache (can disrupt service)
- `/sleep` - Put engine to sleep (causes denial of service)
- `/wake_up` - Wake engine from sleep
- `/is_sleeping` - Check if engine is sleeping