docs: add Windows (WSL2 + CUDA) build guide#12
Open
VatsalyaBhadaurya wants to merge 1 commit into
Open
Conversation
vla.cpp targets Linux/macOS; on Windows the supported path is WSL2 with Ubuntu. Document the GPU/toolkit prerequisites (WSL CUDA driver vs. the in-WSL CUDA toolkit), the apt + CUDA 12.6 setup, the Windows PATH translation gotcha, and the CUDA configure/build/run steps for SmolVLA. Link the new doc from the README alongside the macOS/Metal note.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a Windows build guide for
vla.cppvia WSL2 + CUDA, mirroring the existing macOS/Metal doc.What this adds
docs/backend/windows-wsl.md— WSL2 (Ubuntu 24.04) + CUDA 12.6 setup: GPU/toolkit prerequisites (WSL CUDA driver vs. the in-WSL CUDA toolkit), apt build deps, the WindowsPATHtranslation gotcha (UtilTranslatePathListerrors from stale entries), and the CUDA configure/build/run steps for SmolVLA.README.md— pointer to the new doc alongside the macOS/Metal note.Verification status
Verified through toolchain + dependency setup on Ubuntu 24.04 (WSL2), CUDA 12.6, RTX 4050 Laptop (sm_89). End-to-end CUDA build + SmolVLA load validation is in progress; opening as a draft until the Results section is filled in.