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

[Frontend] Use engine argument to control MM cache size (#22441)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-08 00:47:10 +08:00
committed by GitHub
parent 8c9da6be22
commit 139d155781
13 changed files with 101 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/offline_inference/vision_language.py
View File

@@ -1563,7 +1563,7 @@ def parse_args():
)
parser.add_argument(
"--disable-mm-preprocessor-cache",
"--disable-mm-processor-cache",
action="store_true",
help="If True, disables caching of multi-modal processor.",
)
@@ -1603,7 +1603,7 @@ def main(args):
engine_args = asdict(req_data.engine_args) | {
"seed": args.seed,
"disable_mm_preprocessor_cache": args.disable_mm_preprocessor_cache,
"mm_processor_cache_gb": 0 if args.disable_mm_processor_cache else 4,
}
llm = LLM(**engine_args)