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 15, 18:30 UTC
[Doc] Add guidance for using `ccache` with `pip install -e .` in doc (#14901)
Vadim Gimpelson committed
Mar 17, 2025 at 03:10 UTC
90df7f23aadad4aafc509fa950bd9b967a996e84
1 file changed
+2
docs/source/getting_started/installation/gpu/cuda.inc.md
+2
@@ -131,6 +131,8 @@ Building from source requires a lot of compilation. If you are building from sou
131
For example, you can install [ccache](https://github.com/ccache/ccache) using `conda install ccache` or `apt install ccache` .
132
As long as `which ccache` command can find the `ccache` binary, it will be used automatically by the build system. After the first build, subsequent builds will be much faster.
133
134
+When using `ccache` with `pip install -e .`, you should run `CCACHE_NOHASHDIR="true" pip install --no-build-isolation -e .`. This is because `pip` creates a new folder with a random name for each build, preventing `ccache` from recognizing that the same files are being built.
135
+
136
[sccache](https://github.com/mozilla/sccache) works similarly to `ccache`, but has the capability to utilize caching in remote storage environments.
137
The following environment variables can be set to configure the vLLM `sccache` remote: `SCCACHE_BUCKET=vllm-build-sccache SCCACHE_REGION=us-west-2 SCCACHE_S3_NO_CREDENTIALS=1`. We also recommend setting `SCCACHE_IDLE_TIMEOUT=0`.
138
:::