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.

Sign up for GitHub

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

Jump to bottom

[feature]: Support CPU accelerate by using GGUF #87

Open
Aisuko opened this issue May 2, 2024 · 2 comments
Open

[feature]: Support CPU accelerate by using GGUF #87

Aisuko opened this issue May 2, 2024 · 2 comments
Assignees
@Aisuko
Labels
cpu quantization

Comments

@Aisuko
Copy link
Member

Aisuko commented May 2, 2024

https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf?source=post_page-----7d1fa0b0b623--------------------------------
@Aisuko Aisuko changed the title [feature]: Support CPU accelerate [feature]: Support CPU accelerate by using GGUF May 2, 2024
@Aisuko
Copy link
Member Author

Aisuko commented Jun 23, 2024 •
edited
Loading

Hugging Face transformers already support gguf. However, only several model architectures. So, we will do some test first. If it is ok we will suppert CPU accelerate smoothly. More detail see our discussion

@Aisuko Aisuko self-assigned this Jun 23, 2024
@Aisuko Aisuko mentioned this issue Jun 23, 2024
Closed
2 tasks
@Aisuko
Copy link
Member Author

Aisuko commented Jun 26, 2024

Currently, we support CPU inference accelerate using llama.cpp. However, we will keep working on kimchima repo. We need to implement the CPT and fine-tune in kimchima

@Aisuko Aisuko removed the llms label Aug 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Aisuko Aisuko

Labels
cpu quantization
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Aisuko