Skip to content

Conversation

ochougul
Copy link
Contributor

  • added mxfp4 quantizer to match weights keys
  • added transform to dequantize mxfp4 to float32

…FAutoModelForCausalLM

Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
@ochougul ochougul self-assigned this Sep 26, 2025
@ochougul ochougul added the enhancement New feature or request label Sep 26, 2025
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Copy link
Contributor

@vbaddi vbaddi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks :)
Let's merge this add_gpt_oss, @quic-hemagnih can you please initiate CI and merge the add_gpt_oss branch to mainline?

Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
Signed-off-by: Onkar Chougule <ochougul@qti.qualcomm.com>
@ochougul ochougul merged commit 3adccf6 into add_gpt_oss Oct 8, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request quantization

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants