Skip to content
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.

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

Container multiple python versions #171

Merged
merged 7 commits into from
Jan 22, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
13 changes: 9 additions & 4 deletions .github/workflows/release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,8 @@ jobs:

docker:
name: Build and push containers to registries
runs-on: ubuntu-latest
runs-on:
group: aws-highmemory-32-plus
permissions:
contents: read
attestations: write
Expand Down Expand Up @@ -65,14 +66,18 @@ jobs:
path: tensorrt-llm
repository: nvidia/tensorrt-llm
submodules: true
lfs: true
fetch-depth: 1
ref: v${{ env.TENSORRT_LLM_VERSION }}

- name: Build TensorRT-LLM base image
id: build-tensorrt-llm-base
env:
TARGET_CUDA_ARCHS: "75-real;80-real;86-real;89-real;90-real"
run: cd tensorrt-llm && make -C docker release_build PYTHON_VERSION=${{ matrix.python-version }} CUDA_ARCHS=${{ env.TARGET_CUDA_ARCHS }}
run: |
cd tensorrt-llm
make -C docker release_build \
IMAGE_TAG=v${{ env.TENSORRT_LLM_VERSION}}-py${{ matrix.python-version }} \
CUDA_ARCHS="75-real;80-real;86-real;89-real;90-real" \
PYTHON_VERSION=${{ matrix.python-version }}

- name: Check out the repo
uses: actions/checkout@v4
Expand Down
10 changes: 3 additions & 7 deletions docker/Dockerfile
Original file line number Diff line number Diff line change
@@ -1,11 +1,7 @@
FROM tensorrt_llm/release:latest
ARG PYTHON_VERSION=3.10
ARG TENSORRT_LLM_VERSION

# 75 = T4/RTX Quadro
# 80 = A100/A30
# 86 = A10/A40/RTX Axxx
# 89 = L4/L40/L40s/RTX Ada/4090
# 90 = H100/H200
#ARG TARGET_CUDA_ARCHS="75-real;80-real;86-real;89-real;90-real"
FROM tensorrt_llm/release:v$TENSORRT_LLM_VERSION-py$PYTHON_VERSION

COPY . /opt/optimum-nvidia

Expand Down
Loading