[CPU][Zen] Route W8A8 and W4A16 linear inference through zentorch on AMD Zen CPUs (#41813)

Signed-off-by: R <Ganesh.R@amd.com>
Signed-off-by: Harshal Adhav <harshal.adhav@amd.com>
Signed-off-by: Aakar Dwivedi <aadwived@amd.com>
Co-authored-by: R <Ganesh.R@amd.com>
Co-authored-by: Harshal Adhav <harshal.adhav@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Aakar Dwivedi
2026-05-30 14:17:21 -05:00
committed by GitHub
co-authored by R Harshal Adhav Cursor Michael Goin
parent 27fa5aa3b9
commit 3fd9d2d357
7 changed files with 351 additions and 4 deletions
+1 -3
View File
@@ -1165,9 +1165,7 @@ setup(
install_requires=get_requirements(),
extras_require={
# AMD Zen CPU optimizations via zentorch
"zen": [
"zentorch-weekly==5.2.1.dev20260408"
], # Zentorch has weekly releases. This pulls the known-good version.
"zen": ["zentorch==2.11.0.0"],
"bench": ["pandas", "matplotlib", "seaborn", "datasets", "scipy", "plotly"],
"tensorizer": ["tensorizer==2.10.1"],
"fastsafetensors": ["fastsafetensors >= 0.2.2"],