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

Adding iOS Support to Mistral.rs #63

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

OptimusLime
Copy link

Due to crashes during either new_metal device calls or resource allocation (see issue on Candle main)

  1. Replaced references to MTLResourceOptions::StorageMode* enums to METAL_SHARED_BUFFER_STORAGE_MODE
  2. added libMetalFlashAttention.ios.metalib from release lib of metal flash attention
  3. returned LayerNorm bias to Option as memory overflow on 1B llama 3 was happening in iOS due to LayerNorm

Tested working on iOS 18.2 iphone14 pro and iphone 16 pro.

1. Replaced references to MTLResourceOptions::StorageMode enums to METAL_SHARED_BUFFER_STORAGE_MODE
2. added libMetalFlashAttention.ios.metalib from release lib of metal flash attention lib
3. returned LayerNorm bias to Some as memory overflow on 1B llama 3 was happening in ios.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant