-
Notifications
You must be signed in to change notification settings - Fork 11.2k
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
Vulkan: RTE rounding for cpy to quant #12480
Conversation
The changes look good to me, but I haven't tested locally. |
I just tested these changes in sdcpp, LoRAs still load properly on quantized models, image quality (with LoRA) seemed slightly better with this PR compared to the current implementation, but that might just be luck or placebo effect. |
Co-Authored-By: Jeff Bolz <jbolz@nvidia.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you!
* Vulkan: RTE rounding for cpy to quant Co-Authored-By: Jeff Bolz <jbolz@nvidia.com> * remove trailing whitespace * avoid duplicating pipeline_cpy_f32_quant * fix copypasting issue * remove duplicated code --------- Co-Authored-By: Jeff Bolz <jbolz@nvidia.com>
* Vulkan: RTE rounding for cpy to quant Co-Authored-By: Jeff Bolz <jbolz@nvidia.com> * remove trailing whitespace * avoid duplicating pipeline_cpy_f32_quant * fix copypasting issue * remove duplicated code --------- Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
Fixes some failing tests
Discussed here: #11166
@jeffbolznv