[ET-VK][int4] Wrap int4 linear calls with view_copy nodes to squeeze/unsqueeze inputs#8254

Merged

kirklandsign merged 3 commits intomainfrom

gh/nathanaelsee/3/orig

Feb 6, 2025

Commits on Feb 6, 2025

[ET-VK][int4] patch 4-bit source transformation quantizer to support linear modules with biases
Nathanael See
committed
[ET-VK][int4] patch 4-bit linear op for ensuring w-packed in/out
Nathanael See
committed
[ET-VK][int4] Wrap int4 linear calls with view_copy nodes to squeeze/unsqueeze inputs
Nathanael See
committed