Add Metal (Apple Silicon) support #1819
Closed
Conversation
This file contains 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
- Add Metal device type and support functions - Create Metal backend implementation - Add Metal-specific memory management - Update device dispatch for Metal - Add CMake configuration for Metal This adds support for Apple's Metal framework to improve performance on Apple Silicon devices. The implementation: 1. Adds Metal as a new device type 2. Implements device management and memory operations 3. Provides proper fallback mechanisms 4. Integrates with existing device dispatch system 5. Adds CMake configuration for Metal support
|
Wait, why was this closed? As a macbook pro user, this would be fantastic to have |
|
I am not done with this. My current implementation also is already much better. When I am done I will move to a mojo version of this as that can then again be about at least 6 times faster Will notify you when I am ready. This was created automaticly by https://codeium.com/windsurf have fun with this and do not forget to take breaks ;) |
|
why it's not merged , I waited for this for long to use my M3 GPU |
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Outdated suggestions cannot be applied.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.
This PR adds support for Apple's Metal framework to improve performance on Apple Silicon devices.
Key Changes:
Implementation Details:
Testing:
Notes:
This implementation follows CTranslate2's design patterns and provides a foundation for Metal-accelerated computation on Apple Silicon devices.