xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 06:34:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix entrypoints metrics tests (#18063)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-05-13 21:42:43 +08:00 committed by GitHub
parent 00b14e0f16
commit b922c2ebd2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/api_server.py
View File

@ -150,10 +150,6 @@ async def build_async_engine_client(
async with build_async_engine_client_from_engine_args(
engine_args, args.disable_frontend_multiprocessing) as engine:
# Don't keep the dummy data in memory
await engine.reset_mm_cache()
yield engine
@ -189,6 +185,10 @@ async def build_async_engine_client_from_engine_args(
usage_context=usage_context,
disable_log_requests=engine_args.disable_log_requests,
disable_log_stats=engine_args.disable_log_stats)
# Don't keep the dummy data in memory
await async_llm.reset_mm_cache()
yield async_llm
finally:
if async_llm:

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

@ -289,7 +289,7 @@ class EngineCore:
def reset_mm_cache(self):
# NOTE: Since this is mainly for debugging, we don't attempt to
# re-sync the internal caches (P0 processor, P0 mirror, P1 mirror)
if self.scheduler.get_num_unfinished_requests():
if self.scheduler.has_unfinished_requests():
logger.warning("Resetting the multi-modal cache when requests are "
"in progress may lead to desynced internal caches.")