Skip to content

Removing unused values for TensorRT-LLM container build #8472

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mc-nv merged 5 commits into from
Oct 27, 2025
Merged

Removing unused values for TensorRT-LLM container build #8472

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
64b3ba0
remove obsolete instructions
mc-nv Oct 22, 2025
a125aba
Installing proto as dependency for TensorRT-LLM
mc-nv Oct 23, 2025
8763244
Revert "Installing proto as dependency for TensorRT-LLM"
mc-nv Oct 24, 2025
05113a3
Fix version value
mc-nv Oct 24, 2025
60737ab
Reapply "Installing proto as dependency for TensorRT-LLM"
mc-nv Oct 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 3 additions & 12 deletions build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1283,10 +1283,9 @@ def create_dockerfile_linux(
pip3 uninstall -y setuptools
ENV LD_LIBRARY_PATH=/usr/local/tensorrt/lib/:/opt/tritonserver/backends/tensorrtllm:$LD_LIBRARY_PATH

# There are some ucc issues when spawning mpi processes with ompi v4.1.7a1.
# Downgrade to ompi v4.1.5rc2 to avoid the issue.
RUN rm -fr /opt/hpcx/ompi
COPY --from=nvcr.io/nvidia/tritonserver:24.02-py3-min /opt/hpcx/ompi /opt/hpcx/ompi
RUN apt-get update && apt-get install -y --no-install-recommends \
libprotobuf-dev \
&& rm -rf /var/lib/apt/lists/*
"""
with open(os.path.join(ddir, dockerfile_name), "w") as dfile:
dfile.write(df)
Expand Down Expand Up @@ -1465,14 +1464,6 @@ def dockerfile_prepare_container_linux(argmap, backends, enable_gpu, target_mach
virtualenv \\
&& rm -rf /var/lib/apt/lists/*
"""
if "tensorrtllm" in backends:
df += """
# Updating the openssh-client to fix for the CVE-2024-6387. This can be removed when trtllm uses a later CUDA container(12.5 or later)
RUN apt-get update \\
&& apt-get install -y --no-install-recommends \\
openssh-client \\
&& rm -rf /var/lib/apt/lists/*
"""

if "vllm" in backends:
df += f"""
Expand Down
Loading