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
Why doesn't AutoGPTQ quantize lm_head layer? #647
Comments
@XeonKHJ Good question. I will test this tomorrow with intel/auto-round that does offer the ability to quantize lm-head. If there are no inference issues post quantize, I will make it as an option in new PR. |
Found intel's results of quantization test of lm-head. There was minimal accuracy loss: @wenhuach21 Do you know how much ram/vram the intel llama3-8B lm_head quantized test saved vs non-quantized? Here is the untested branch that allows loading of quanted lm-head that I plan to test: https://github.com/Qubitium/AutoGPTQ/tree/sym-false-lm-head combined with intel/auto-round#87
|
What I know is the model size at W4G128, W/O lm head 5.4G, with lm head 4.7G. Additionally, if act-order is not enabled or static group is enabled, could Autogptq refrain from dumping the group index into the quantized model, thus conserving some resources |
#648 can now load quantized |
Is there a paper/article/blog post explaining such decision? Or is it just simply a feature that not being supported at the moment?
The text was updated successfully, but these errors were encountered: