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 15, 06:00 UTC
[doc] fix the incorrect label (#19787)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jun 18, 2025 at 18:30 UTC
cca91a7a10c8227984311444e4ba901e7c54cf34
2 files changed
+1
-3
docs/getting_started/installation/gpu.md
+1
-1
@@ -42,7 +42,7 @@ vLLM is a Python library that supports the following GPU variants. Select your G
42
43
=== "NVIDIA CUDA"
44
45
- --8<-- "docs/getting_started/installation/gpu/cuda.inc.md:create-a-new-python-environment"
45
+ --8<-- "docs/getting_started/installation/gpu/cuda.inc.md:set-up-using-python"
46
47
=== "AMD ROCm"
48
docs/getting_started/installation/gpu/cuda.inc.md
-2
@@ -10,8 +10,6 @@ vLLM contains pre-compiled C++ and CUDA (12.8) binaries.
10
# --8<-- [end:requirements]
11
# --8<-- [start:set-up-using-python]
12
13
-### Create a new Python environment
14
-
13
!!! note
14
PyTorch installed via `conda` will statically link `NCCL` library, which can cause issues when vLLM tries to use `NCCL`. See <gh-issue:8420> for more details.
15