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 17, 04:15 UTC
[BugFix] Hot fix in setup.py for neuron build (#3537)
Zhuohan Li committed
Mar 20, 2024 at 17:59 UTC
523e30ea0c5abcb447763dcd9a77b54d5c5f3239
1 file changed
+1
-1
setup.py
+1
-1
@@ -168,7 +168,7 @@ class cmake_build_ext(build_ext):
168
169
170
def _is_cuda() -> bool:
171
- return torch.version.cuda is not None
171
+ return torch.version.cuda is not None and not _is_neuron()
172
173
174
def _is_hip() -> bool: