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