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

quant_config Dtype INT16 support request #136

Open

ZORO-Q opened this issue Aug 8, 2024 · 0 comments

Assignees

Labels

ZORO-Q commented Aug 8, 2024

ai-edge-torch/ai_edge_torch/generative/quantize/quant_attrs.py

Lines 23 to 25 in 301583b

    
           FP32 = enum.auto() 
        
           FP16 = enum.auto() 
        
           INT8 = enum.auto()

The quant_config currently can only support FP32, FP16, INT8, will you consider support INT16? It would be great if it could be supported.

pkgoogle added the type:feature label

haozha111 assigned paulinesho

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment