Skip to content

Commit fae2464

Browse files
committed
minor documentation changes
1 parent d9a7be7 commit fae2464

File tree

1 file changed

+4
-4
lines changed

1 file changed

+4
-4
lines changed

docs/source/getting_started/amd-installation.rst

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ Requirements
1414
* Python: 3.8 -- 3.11
1515
* GPU: MI200s (gfx90a), MI300 (gfx942)
1616
* Pytorch 2.0.1/2.1.1/2.2
17-
* ROCm 5.7 ((Verified on 3.10) or ROCm 6.0 ((Verified on 3.9))
17+
* ROCm 5.7 (Verified on python 3.10) or ROCm 6.0 (Verified on python 3.9)
1818

1919
Installation options:
2020

@@ -97,22 +97,22 @@ You can build and install vLLM from source:
9797

9898
Build a docker image from `Dockerfile.rocm`, and launch a docker container.
9999

100-
The `Dokerfile.rocm` is designed to support both ROCm 5.7 and ROCm 5.8. It provides flexibility to customize the build of docker image using the following arguments:
100+
The `Dokerfile.rocm` is designed to support both ROCm 5.7 and ROCm 6.0. It provides flexibility to customize the build of docker image using the following arguments:
101101

102102
* `BASE_IMAGE`: specifies the base image used when running `docker build`, specifically the PyTorch on ROCm base image. We have tested ROCm 5.7 and ROCm 6.0. The default is `rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1`
103103
* `FX_GFX_ARCHS`: specifies the GFX architecture that is used to build flash-attention, for example, `gfx90a;gfx942` for MI200 and MI300. The default is `gfx90a;gfx942`
104104
* `FA_BRANCH`: specifies the branch used to build the flash-attention in `ROCmSoftwarePlatform's flash-attention repo <https://github.com/ROCmSoftwarePlatform/flash-attention>`_. The default is `3d2b6f5`
105105

106106
Their values can be passed in when running `docker build` with `--build-arg` options.
107107

108-
For example, to build docker image for vllm on ROCm 6.0, we can run:
108+
For example, to build docker image for vllm on ROCm 6.0, you can run:
109109

110110
.. code-block:: console
111111
112112
$ docker build --build-arg BASE_IMAGE="compute-artifactory.amd.com:5000/rocm-plus-docker/framework/release-public:rocm6.0_ubuntu20.04_py3.9_pytorch_rocm6.0_internal_testing" \
113113
-f Dockerfile.rocm -t vllm-rocm .
114114
115-
To build vllm on ROCm 5.7, we can use the default:
115+
To build vllm on ROCm 5.7, you can use the default:
116116

117117
.. code-block:: console
118118

0 commit comments

Comments
 (0)