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, 00:30 UTC
[Doc] add ccache guide in doc (#5012)
Co-authored-by: Michael Goin <michael@neuralmagic.com>
youkaichao committed
May 23, 2024 at 16:21 UTC
6a50f4cafaf9f734b3f6ad11e6af38838aa3baf8
1 file changed
+4
docs/source/getting_started/installation.rst
+4
@@ -56,6 +56,10 @@ You can also build and install vLLM from source:
56
$ # export VLLM_INSTALL_PUNICA_KERNELS=1 # optionally build for multi-LoRA capability
57
$ pip install -e . # This may take 5-10 minutes.
58
59
+.. tip::
60
+
61
+ Building from source requires quite a lot compilation. If you are building from source for multiple times, it is beneficial to cache the compilation results. For example, you can install `ccache <https://github.com/ccache/ccache>`_ via either `conda install ccache` or `apt install ccache` . As long as `which ccache` command can find the `ccache` binary, it will be used automatically by the build system. After the first build, the subsequent builds will be much faster.
62
+
63
.. tip::
64
To avoid your system being overloaded, you can limit the number of compilation jobs
65
to be run simultaneously, via the environment variable `MAX_JOBS`. For example: