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 16, 20:45 UTC
[Docs] Update docs for wheel location (#6580)
Simon Mo committed
Jul 19, 2024 at 12:14 UTC
30efe41532b7cd7202d128ffedfc703c4039767f
1 file changed
+2
-3
docs/source/getting_started/installation.rst
+2
-3
@@ -49,11 +49,10 @@ You can install vLLM using pip:
49
.. code-block:: console
50
51
$ export VLLM_VERSION=0.5.2 # vLLM's main branch version is currently set to latest released tag
52
- $ export PYTHON_VERSION=310
53
- $ pip install https://vllm-wheels.s3.us-west-2.amazonaws.com/nightly/vllm-${VLLM_VERSION}-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux1_x86_64.whl
52
+ $ pip install https://vllm-wheels.s3.us-west-2.amazonaws.com/nightly/vllm-${VLLM_VERSION}-cp38-abi3-manylinux1_x86_64.whl
53
$ # You can also access a specific commit
54
$ # export VLLM_COMMIT=...
56
- $ # pip install https://vllm-wheels.s3.us-west-2.amazonaws.com/${VLLM_COMMIT}/vllm-${VLLM_VERSION}-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux1_x86_64.whl
55
+ $ # pip install https://vllm-wheels.s3.us-west-2.amazonaws.com/${VLLM_COMMIT}/vllm-${VLLM_VERSION}-cp38-abi3-manylinux1_x86_64.whl
56
57
58
.. _build_from_source: