[Bugfix] Fix SHM cache initialization (#26427)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-10-09 02:48:04 -07:00
committed by GitHub
parent dc7976dd9f
commit 4bdf7ac593
30 changed files with 357 additions and 417 deletions
+1 -1
View File
@@ -186,7 +186,7 @@ async def run_vllm_async(
engine_args,
disable_frontend_multiprocessing=disable_frontend_multiprocessing,
) as llm:
model_config = await llm.get_model_config()
model_config = llm.model_config
assert all(
model_config.max_model_len
>= (request.prompt_len + request.expected_output_len)