docs: add CPU-only PyTorch installation options#22
Merged
JimmyWhitaker merged 1 commit intomainfrom Jan 23, 2026
Merged
Conversation
Add documentation for forcing CPU-only PyTorch installation when running genai-bench on GPU machines. This reduces download size from ~2GB+ to ~200MB since genai-bench primarily uses PyTorch for tokenization, not GPU computation. Two options documented: 1. Using --torch-backend=cpu flag 2. Using UV_TORCH_BACKEND=cpu environment variable Added to both README.md and installation guide.
github-actions
bot
added
the
documentation
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add documentation for forcing CPU-only PyTorch installation when running genai-bench on GPU machines. This reduces download size from ~2GB+ to ~200MB since genai-bench primarily uses PyTorch for tokenization, not GPU computation.
Changes
--torch-backend=cpuflagUV_TORCH_BACKEND=cpuenvironment variableMotivation
When running
uv run -p 3.13 --with git+https://github.com/basetenlabs/genai-bench.git genai-bench benchmarkon GPU machines, UV installs PyTorch GPU wheels by default, which are unnecessarily large and include CUDA runtime. Since genai-bench only uses PyTorch for tokenization (not GPU computation), forcing CPU-only installation significantly reduces download size and installation time.Testing
Verified documentation is clear and complete. Users can now:
--torch-backend=cpuflag to force CPU-only PyTorchUV_TORCH_BACKEND=cpuenvironment variable for global configuration