You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 73ae813
Browse filesBrowse the repository at this point in the historyBrowse files
Vulkan Q8 Conv2D: specialize shader on static parameters and tensor sizes (pytorch#16036)
This change moves all fixed Conv2D parameters (kernel shape, stride,
padding, dilation, groups) and the input/output tensor dimensions into
Vulkan specialization constants. By making these values compile-time
constants, the backend can generate more optimized pipelines, eliminate
generic fallback paths, and reduce dynamic indexing overhead. This
significantly improves performance across large and compute-intensive
convolution workloads.
cc @SS-JIA@manuelcandales@digantdesai@cbilgin
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
0 commit comments