Skip to content

Conversation

@Hzfengsy
Copy link
Member

@Hzfengsy Hzfengsy commented Jun 3, 2024

q4f16_0 may improve the performance of metal. To be specific, Llama-3 8B on M1 Pro:

  1. Single batch 26.2 tok/s (q4f16_1) vs. 28.0 tok/s (q4f16_0)
  2. low-batched serving: about 25% improvement

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.

2 participants