20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Docs] Update installation page (#1005)

Browse Source
This commit is contained in:
Woosuk Kwon 2023-09-10 14:23:31 -07:00 committed by GitHub
parent 898285c9bf
commit b9cecc2635
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
docs/source/getting_started/installation.rst
View File

@ -3,31 +3,15 @@
Installation Installation
============ ============
vLLM is a Python library that also contains some C++ and CUDA code. vLLM is a Python library that also contains pre-compiled C++ and CUDA (11.8) binaries.
This additional code requires compilation on the user's machine.
Requirements Requirements
------------ ------------
* OS: Linux * OS: Linux
* Python: 3.8 or higher * Python: 3.8 -- 3.11
* CUDA: 11.0 -- 11.8
* GPU: compute capability 7.0 or higher (e.g., V100, T4, RTX20xx, A100, L4, etc.) * GPU: compute capability 7.0 or higher (e.g., V100, T4, RTX20xx, A100, L4, etc.)
.. note::
As of now, vLLM does not support CUDA 12.
If you are using Hopper or Lovelace GPUs, please use CUDA 11.8 instead of CUDA 12.
.. tip::
If you have trouble installing vLLM, we recommend using the NVIDIA PyTorch Docker image.
.. code-block:: console
$ # Pull the Docker image with CUDA 11.8.
$ docker run --gpus all -it --rm --shm-size=8g nvcr.io/nvidia/pytorch:22.12-py3
Inside the Docker container, please execute :code:`pip uninstall torch` before installing vLLM.
Install with pip Install with pip
---------------- ----------------
@ -40,7 +24,7 @@ You can install vLLM using pip:
$ conda activate myenv $ conda activate myenv
$ # Install vLLM. $ # Install vLLM.
$ pip install vllm # This may take 5-10 minutes. $ pip install vllm
.. _build_from_source: .. _build_from_source:
@ -55,3 +39,11 @@ You can also build and install vLLM from source:
$ git clone https://github.com/vllm-project/vllm.git $ git clone https://github.com/vllm-project/vllm.git
$ cd vllm $ cd vllm
$ pip install -e . # This may take 5-10 minutes. $ pip install -e . # This may take 5-10 minutes.
.. tip::
If you have trouble building vLLM, we recommend using the NVIDIA PyTorch Docker image.
.. code-block:: console
$ # Pull the Docker image with CUDA 11.8.
$ docker run --gpus all -it --rm --shm-size=8g nvcr.io/nvidia/pytorch:22.12-py3