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 17, 03:00 UTC
[Doc][Installation] delete python setup.py develop (#3989)
youkaichao committed
Apr 10, 2024 at 20:33 UTC
f3d0bf7589d6e63a691dcbb9d1db538c184fde29
1 file changed
-10
docs/source/getting_started/installation.rst
-10
@@ -85,13 +85,3 @@ You can also build and install vLLM from source:
85
86
$ nvcc --version # verify that nvcc is in your PATH
87
$ ${CUDA_HOME}/bin/nvcc --version # verify that nvcc is in your CUDA_HOME
88
-
89
-.. note::
90
- If you are developing the C++ backend of vLLM, consider building vLLM with
91
-
92
- .. code-block:: console
93
-
94
- $ python setup.py develop
95
-
96
- since it will give you incremental builds. The downside is that this method
97
- is `deprecated by setuptools <https://github.com/pypa/setuptools/issues/917>`_.