Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

FEAT: support MLX engine #1765

Merged
merged 8 commits into from
Jul 5, 2024
Merged

FEAT: support MLX engine #1765

merged 8 commits into from
Jul 5, 2024

Conversation

qinxuye
Copy link
Contributor

@qinxuye qinxuye commented Jul 3, 2024

Background

https://github.com/ml-explore/mlx is developed by Apple to enable AI on Apple silicon chips.

Benchmark

M1 MAX (qwen2-instruct,7b)

MLX(4-bit) vs. llama.cpp(q4_k_m)

43.3 tokens/s vs. 31.12 tokens/s

@qinxuye qinxuye mentioned this pull request Jul 3, 2024
@qinxuye qinxuye force-pushed the feat/mlx branch 4 times, most recently from 4324208 to 4e21a16 Compare July 4, 2024 02:41
@qinxuye qinxuye merged commit 3cb1367 into xorbitsai:main Jul 5, 2024
13 checks passed
@qinxuye qinxuye deleted the feat/mlx branch July 5, 2024 04:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants