kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Fix permission for local user issues in NGC docker container. (#5373)

Browse Source 
Signed-off-by: Martin Marciniszyn Mehringer <11665257+MartinMarciniszyn@users.noreply.github.com>
This commit is contained in:
Martin Marciniszyn Mehringer 2025-06-25 14:10:20 +02:00 committed by GitHub
parent b6d23d58c4
commit fc64f139e4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docker/Dockerfile.user
View File

@ -9,9 +9,9 @@ ARG GROUP_ID=0
ARG GROUP_NAME=root
RUN (getent group ${GROUP_ID} || groupadd --gid ${GROUP_ID} ${GROUP_NAME}) && \
(getent passwd ${USER_ID} || useradd --gid ${GROUP_ID} --uid ${USER_ID} --create-home --no-log-init --shell /bin/bash ${USER_NAME})
RUN apt-get update && \
(getent passwd ${USER_ID} || useradd --gid ${GROUP_ID} --uid ${USER_ID} --create-home --no-log-init --shell /bin/bash ${USER_NAME}) && \
chown ${USER_NAME}:${GROUP_NAME} /app/tensorrt_llm && \
apt-get update && \
apt-get install -y sudo && \
adduser ${USER_NAME} sudo && \
echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers && \

1
docker/Makefile
View File

@ -138,6 +138,7 @@ endif
docker run $(DOCKER_RUN_OPTS) $(DOCKER_RUN_ARGS) \
$(GPU_OPTS) \
--volume $(SOURCE_DIR):$(CODE_DIR) \
$(if $(filter 1,$(LOCAL_USER)),--volume ${HOME}/.cache:/home/${USER_NAME}/.cache:rw) \
--env "CCACHE_DIR=${CCACHE_DIR}" \
--env "CCACHE_BASEDIR=${CODE_DIR}" \
--env "CONAN_HOME=${CONAN_DIR}" \

2
docs/source/quick-start-guide.md
View File

@ -4,7 +4,7 @@
This is the starting point to try out TensorRT-LLM. Specifically, this Quick Start Guide enables you to quickly get setup and send HTTP requests using TensorRT-LLM.
The following examples can most easily be executed using the prebuilt [Docker release container available on NGC](https://registry.ngc.nvidia.com/orgs/nvstaging/teams/tensorrt-llm/containers/release) (see also [release.md](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docker/release.md) on GitHub). Ensure to run these commands as a user with appropriate permissions, preferably `root`, to streamline the setup process.
The following examples can most easily be executed using the prebuilt [Docker release container available on NGC](https://registry.ngc.nvidia.com/orgs/nvstaging/teams/tensorrt-llm/containers/release) (see also [release.md](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docker/release.md) on GitHub).
## LLM API