SIGN IN SIGN UP

[ExecuTorch][llm] Fuse w1+w3 into single GEMM in quantized_moe_ffn (#21538)

This PR was created by the merge bot to help merge the original PR into
the main branch.
ghstack PR number: https://github.com/pytorch/executorch/pull/21124 by
@digantdesai
^ Please use this as the source of truth for the PR details, comments,
and reviews
ghstack PR base:
https://github.com/pytorch/executorch/tree/gh/digantdesai/74/base
ghstack PR head:
https://github.com/pytorch/executorch/tree/gh/digantdesai/74/head
Merge bot PR base:
https://github.com/pytorch/executorch/tree/gh/digantdesai/73/orig
Merge bot PR head:
https://github.com/pytorch/executorch/tree/gh/digantdesai/74/orig
Differential Revision:
[D102799854](https://our.internmc.facebook.com/intern/diff/D102799854/)
@diff-train-skip-merge

Co-authored-by: Digant Desai <digantdesai@meta.com>
P
pytorchbot committed
cb5e32fa80769062a6ee34c5a210708d4c4e9f6d
Parent: 24ff58a
Committed by GitHub <noreply@github.com> on 8/1/2026, 2:03:00 PM