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.

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

src: attr: quantization refactor (part 3) #2746

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

dzarukin
Copy link
Contributor

This is the finishing part of quantization refactor that beautifies skip_mask values for scales and zero-points and introduces a single class for both of them with ability to extend one over the other.

@dzarukin dzarukin requested review from a team as code owners February 24, 2025 21:54
@github-actions github-actions bot added platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic labels Feb 24, 2025
@dzarukin
Copy link
Contributor Author

make test
enable arch_gpu_ampere
enable compiler_icx-oss

Copy link
Contributor

@mgouicem mgouicem left a comment

Choose a reason for hiding this comment

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

(nit) would it makes sense to also remove usage of DNNL_ARG_ATTR_OUTPUT_SCALES from primitive_exec_types.cpp and miopen_{convolution,inner_product}.cpp as part of this PR?

@dzarukin dzarukin force-pushed the dzarukin/quant_styling branch from cf9b2da to 4478b31 Compare February 26, 2025 00:12
@github-actions github-actions bot added the component:api Codeowner: @oneapi-src/onednn-arch label Feb 26, 2025
@dzarukin dzarukin force-pushed the dzarukin/quant_styling branch from 4478b31 to e444113 Compare February 27, 2025 23:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:api Codeowner: @oneapi-src/onednn-arch platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64 platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants