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

[BUG] Reset running requests when clearing cache for pause/resume (#34382)

Browse Source 
Signed-off-by: hao-aaron <ahao@anyscale.com>
This commit is contained in:
Aaron Hao
2026-02-12 08:19:13 -08:00
committed by GitHub
parent dea63512bb
commit 7b5a8b4a9d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/engine/async_llm.py
View File

@@ -793,7 +793,7 @@ class AsyncLLM(EngineClient):
# Clear cache # Clear cache
if clear_cache: if clear_cache:
await self.reset_prefix_cache() await self.reset_prefix_cache(reset_running_requests=True)
await self.reset_mm_cache() await self.reset_mm_cache()
await self.reset_encoder_cache() await self.reset_encoder_cache()