oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-03-06 21:53:50 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update TensorRT-LLM Dockerfile for v1.1.0

Browse source
This commit is contained in:
oobabooga 2026-03-05 06:17:52 -08:00
parent 45188eccef
commit b16a1a874a
1 changed files with 10 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
docker/TensorRT-LLM/Dockerfile
View file

@ -1,27 +1,24 @@
FROM pytorch/pytorch:2.9.1-cuda12.8-cudnn9-runtime
FROM nvidia/cuda:13.0.1-cudnn-runtime-ubuntu24.04
# Install Git
RUN apt update && apt install -y git
# System-wide TensorRT-LLM requirements
RUN apt install -y openmpi-bin libopenmpi-dev
# Install Python 3.12, Git, and OpenMPI
RUN apt update && apt install -y python3.12 python3-pip git build-essential openmpi-bin libopenmpi-dev
# Set the working directory
WORKDIR /app
# Install text-generation-webui
RUN git clone https://github.com/oobabooga/text-generation-webui
WORKDIR /app/text-generation-webui
RUN pip install -r requirements/full/requirements.txt
# This is needed to avoid an error about "Failed to build mpi4py" in the next command
ENV LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
# Install text-generation-webui
RUN git clone https://github.com/oobabooga/text-generation-webui
WORKDIR /app/text-generation-webui
RUN pip install --break-system-packages -r requirements/full/requirements.txt
# Install TensorRT-LLM
RUN pip3 install tensorrt_llm==1.1.0 -U --extra-index-url https://pypi.nvidia.com
RUN pip3 install --break-system-packages tensorrt_llm==1.1.0 --extra-index-url https://pypi.nvidia.com
# Expose the necessary port for the Python server
EXPOSE 7860 5000
# Run the Python server.py script with the specified command
CMD ["python", "server.py", "--api", "--listen"]
CMD ["python3", "server.py", "--api", "--listen"]