Repository navigation
Add Docker GPU support and deployment docs - #279
Merged
Merged
Conversation
- Add Dockerfile.gpu using nvidia/cuda:12.1.1-runtime for smaller image - Add gpu service to docker-compose.yml on port 7861 - Add docs/docker-gpu.md covering prerequisites, NVIDIA Container Toolkit installation, VRAM requirements by GPU tier, verification, troubleshooting - Update README, docs/index.md, docs/install.md, tutorials/deployment.md to reference GPU Docker setup Closes #232
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Dockerfile.gpubased onnvidia/cuda:12.1.1-runtime-ubuntu22.04for GPU inference with a smaller image footprint than the existing devel-basedDockerfilegpuservice todocker-compose.ymlon port 7861, keeping the existingapp-gpuservice for backward compatibilitydocs/docker-gpu.mdwith comprehensive GPU Docker setup guide covering NVIDIA Container Toolkit installation, VRAM requirements by GPU tier (8GB/12GB/24GB+), verification steps, multi-GPU configuration, and troubleshootingdocs/index.md,docs/install.md, anddocs/tutorials/deployment.mdto reference the new GPU guideCloses #232
Test plan
docker build -f Dockerfile.gpu -t landmarkdiff:gpu .builds successfullydocker compose up gpustarts the GPU service on port 7861docker run --gpus all landmarkdiff:gpu python -c "import torch; print(torch.cuda.is_available())"returns Truedocs/docker-gpu.mdrenders properly in Sphinx/GitHub