perf: reduce GPU Docker image size by ~56% using CUDA 12.4 runtime#69
Merged
Conversation
Switch from manually copying CUDA libraries from devel image to using the official nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04 base image. Changes: - Update katago-gpu-builder to use CUDA 12.4.1-cudnn-devel (includes cuDNN) - Update gpu, human-gpu, combo-gpu stages to use cudnn-runtime base - Remove manual library copying (libcublas*, libcudnn*) which caused bloat - Simplify runtime dependency installation Size reduction (compressed): - combo-gpu: ~5.5 GB → ~2.4 GB (~56% reduction) - gpu: ~5.3 GB → ~2.2 GB (~58% reduction) - human-gpu: ~5.1 GB → ~2.1 GB (~59% reduction) CUDA 12.4 requires driver >= 525.60.13 which is compatible with: - RTX 3080 (10 GB) on Salad Cloud - All modern NVIDIA GPUs with recent drivers 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04base imageChanges
katago-gpu-builderto usenvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04(cuDNN included)gpu,human-gpu,combo-gpustages to usenvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04libcublas*,libcudnn*) which was causing ~5.3 GB bloatSize Reduction
Test plan
🤖 Generated with Claude Code