Skip to content

[WebGPU EP] Fuse QMoE 1-token decode path to reduce GPU dispatches#27998

Merged
guschmue merged 12 commits intomainfrom
opt/webgpu-qmoe-fused-1token
Apr 10, 2026
Merged

[WebGPU EP] Fuse QMoE 1-token decode path to reduce GPU dispatches#27998
guschmue merged 12 commits intomainfrom
opt/webgpu-qmoe-fused-1token

Commits

Commits on Apr 7, 2026

Commits on Apr 8, 2026

Commits on Apr 9, 2026