Fix: Add early check for macOS incompatibility with flashinfer/triton #2
Conversation
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
- Introduced a new module, `environment.py`, to check platform compatibility for flashinfer and Triton. - Added a function `is_flashinfer_supported()` to verify if flashinfer is usable on the current platform, with specific checks for unsupported macOS. - Added `assert_flashinfer_supported()` in `entry.py` to raise a `RuntimeError` when the platform is not supported. - Ensures users receive a clear error message to prevent execution on incompatible systems.
Updated the README.md to include a section on platform compatibility. Added details indicating that Tokasaurus uses `flashinfer` and relies on Triton, which is not supported on macOS due to the lack of CUDA. Users on macOS may experience a `ModuleNotFoundError` for Triton. Recommended running Tokasaurus in a Linux environment with a CUDA-compatible GPU to ensure full functionality.
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Outdated suggestions cannot be applied.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.
This PR adds an early runtime check to catch macOS incompatibility due to
flashinfer's dependency ontriton, which is not supported on macOS.This prevents obscure crashes (
ModuleNotFoundError: triton) and replaces them with a clear, actionable error message:RuntimeError: Tokasaurus currently depends on flashinfer, which in turn requires ‘triton’.
However, ‘triton’ is not supported on macOS.
Please run Tokasaurus in a Linux environment with a supported GPU.
Implementation
assert_flashinfer_supported()intokasaurus/environment.pyentry.pybefore any indirect flashinfer importsThis improves the developer experience for macOS users without affecting behavior on Linux.
Output: