[ET-VK] Minor improvement to q_linear op shader. (#7932)
Pull Request resolved: https://github.com/pytorch/executorch/pull/7728 This diff contains a minor improvement to the q_linear op shader in the Vulkan backend for Executorch. The code changes in the q_8w_linear.glsl file include a change in position parameter from a 3-element u16vec3 to a 2-element u16vec2. ghstack-source-id: 262853434 Differential Revision: [D68113154](https://our.internmc.facebook.com/intern/diff/D68113154/) Co-authored-by: Vivek Trivedi <5340687+trivedivivek@users.noreply.github.com>
P
pytorchbot committed
b043e0d035a3d39d4e430aa96cb1f76bda2cf40d
Parent: 57ef834
Committed by GitHub <noreply@github.com>
on 1/24/2025, 3:39:54 PM