@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / f70bccac75
Fork 0

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, 15:45 UTC

[Build/CI] Upgrade to gcc 10 in the base build Docker image (#8814)

Tyler Michael Smith committed Sep 26, 2024 at 13:07 UTC f70bccac75a0aecc0a5fc934859158a3e1f019a5
1 file changed +8
Dockerfile
+8
@@ -27,6 +27,14 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
27 && curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
28 && python3 --version && python3 -m pip --version
29
30 +# Upgrade to GCC 10 to avoid https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92519
31 +# as it was causing spam when compiling the CUTLASS kernels
32 +RUN apt-get install -y gcc-10 g++-10
33 +RUN update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-10 110 --slave /usr/bin/g++ g++ /usr/bin/g++-10
34 +RUN <<EOF
35 +gcc --version
36 +EOF
37 +
38 # Workaround for https://github.com/openai/triton/issues/2507 and
39 # https://github.com/pytorch/pytorch/issues/107960 -- hopefully
40 # this won't be needed for future versions of this docker image