A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Core][Multimodal] Cache `supports_kw` (#24773)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Lukas Geiger committed
Sep 13, 2025 at 08:27 UTC
1da0f1441d934c4fa9257fdc6807da30b52e38a3
1 file changed
+1
vllm/utils/__init__.py
+1
@@ -2082,6 +2082,7 @@ async def _run_task_with_lock(task: Callable, lock: asyncio.Lock, *args,
2082
return await task(*args, **kwargs)
2083
2084
2085
+@lru_cache
2086
def supports_kw(
2087
callable: Callable[..., object],
2088
kw_name: str,