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 13, 04:30 UTC
Fix typo in comment: existance -> existence (#28737)
Signed-off-by: Mohammad Othman <emranm226@hotmail.com>
Mohammad Othman committed
Nov 14, 2025 at 19:35 UTC
a17e36f2236a15012c8ddfedbf076a526de4b17b
1 file changed
+1
-1
vllm/_aiter_ops.py
+1
-1
@@ -30,7 +30,7 @@ def if_aiter_supported(func: Callable) -> Callable:
30
31
@functools.wraps(func)
32
def wrapper(*args, **kwargs):
33
- # checks the platform, device arch and aiter library existance.
33
+ # checks the platform, device arch and aiter library existence.
34
35
if current_platform.is_rocm() and IS_AITER_FOUND:
36
from vllm.platforms.rocm import on_gfx9