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, 22:35 UTC
[BUG] [ROCm] Fix import bug on ROCm (#22083)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
TJian committed
Aug 1, 2025 at 05:25 UTC
26b5f7bd2a4005dccb797804c93cbce329253003
1 file changed
+1
-1
vllm/compilation/pass_manager.py
+1
-1
@@ -7,7 +7,7 @@ from vllm.config import VllmConfig
7
from vllm.logger import init_logger
8
from vllm.platforms import current_platform
9
10
-if current_platform.is_cuda_alike():
10
+if current_platform.is_cuda():
11
from .fusion import FusionPass
12
from .collective_fusion import AllReduceFusionPass, AsyncTPPass
13
from .fusion_attn import AttnFusionPass