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

[PR Ready for Review] [FEATURE] Extend Support for Phi-3 #652

Open
davidgxue opened this issue Apr 27, 2024 · 0 comments · May be fixed by #651
Open

[PR Ready for Review] [FEATURE] Extend Support for Phi-3 #652

davidgxue opened this issue Apr 27, 2024 · 0 comments · May be fixed by #651
Labels
enhancement New feature or request

Comments

@davidgxue
Copy link

davidgxue commented Apr 27, 2024 •
edited

Is your feature request related to a problem? Please describe.
Extend AutoGPTQ support for Microsoft's recently released Phi-3 models

Describe the solution you'd like
I have a PR ready and tested on my end to allow Phi-3-mini variants to be quantized using AutoGPTQ library.

Please see my PR here: #651

Additional context
I think there's minor concerns regarding the fact that Phi 3 has its MLP and QKV fused... This can be discussed in my PR I raised in detail
@davidgxue davidgxue added the enhancement New feature or request label Apr 27, 2024
@davidgxue davidgxue linked a pull request Apr 27, 2024 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Extend support for Phi-3 models davidgxue/AutoGPTQ
1 participant
@davidgxue