You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Note: PyTorch 2.5+/ROCm6.2 dropped the support for python 3.8.
15
17
16
18
Installation options:
17
19
@@ -27,7 +29,7 @@ You can build and install vLLM from source.
27
29
28
30
First, build a docker image from `Dockerfile.rocm <https://github.com/vllm-project/vllm/blob/main/Dockerfile.rocm>`_ and launch a docker container from the image.
29
31
30
-
`Dockerfile.rocm <https://github.com/vllm-project/vllm/blob/main/Dockerfile.rocm>`_ uses ROCm 6.1 by default, but also supports ROCm 5.7and 6.0 in older vLLM branches.
32
+
`Dockerfile.rocm <https://github.com/vllm-project/vllm/blob/main/Dockerfile.rocm>`_ uses ROCm 6.2 by default, but also supports ROCm 5.7, 6.0 and 6.1 in older vLLM branches.
31
33
It provides flexibility to customize the build of docker image using the following arguments:
32
34
33
35
* `BASE_IMAGE`: specifies the base image used when running ``docker build``, specifically the PyTorch on ROCm base image.
@@ -39,13 +41,13 @@ It provides flexibility to customize the build of docker image using the followi
39
41
Their values can be passed in when running ``docker build`` with ``--build-arg`` options.
40
42
41
43
42
-
To build vllm on ROCm 6.1 for MI200 and MI300 series, you can use the default:
44
+
To build vllm on ROCm 6.2 for MI200 and MI300 series, you can use the default:
For installing PyTorch, you can start from a fresh docker image, e.g, `rocm/pytorch:rocm6.1.2_ubuntu20.04_py3.9_pytorch_staging`, `rocm/pytorch-nightly`.
85
+
For installing PyTorch, you can start from a fresh docker image, e.g, `rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0`, `rocm/pytorch-nightly`.
85
86
86
87
Alternatively, you can install PyTorch using PyTorch wheels. You can check PyTorch installation guide in PyTorch `Getting Started <https://pytorch.org/get-started/locally/>`_
87
88
@@ -90,34 +91,53 @@ Alternatively, you can install PyTorch using PyTorch wheels. You can check PyTor
90
91
91
92
Install ROCm's Triton flash attention (the default triton-mlir branch) following the instructions from `ROCm/triton <https://github.com/ROCm/triton/blob/triton-mlir/README.md>`_
- If you see HTTP issue related to downloading packages during building triton, please try again as the HTTP error is intermittent.
107
+
108
+
93
109
2. Optionally, if you choose to use CK flash attention, you can install `flash attention for ROCm <https://github.com/ROCm/flash-attention/tree/ck_tile>`_
94
110
111
+
95
112
Install ROCm's flash attention (v2.5.9.post1) following the instructions from `ROCm/flash-attention <https://github.com/ROCm/flash-attention/tree/ck_tile#amd-gpurocm-support>`_
96
113
Alternatively, wheels intended for vLLM use can be accessed under the releases.
97
114
98
-
.. note::
99
-
- You might need to downgrade the "ninja" version to 1.10 it is not used when compiling flash-attention-2 (e.g. `pip install ninja==1.10.2.4`)
115
+
For example, for ROCm 6.2, suppose your gfx arch is `gfx90a`.
116
+
Note to get your gfx architecture, run `rocminfo |grep gfx`.
100
117
101
-
3. Build vLLM.
102
-
103
-
.. code-block:: console
118
+
.. code-block:: console
104
119
105
-
$ cd vllm
106
-
$ pip install -U -r requirements-rocm.txt
107
-
$ python setup.py develop # This may take 5-10 minutes. Currently, `pip install .` does not work for ROCm installation
0 commit comments