SIGN IN SIGN UP

metal : faster q4_0 (#1775)

* metal : 8% faster q4_0

Avoid copying into local uchar4 anf float4.

* metal : 17% faster Q4_0

Use 64 threads in a thread group.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
K
Kawrakow committed
245fc3c37da5ac5963f9f11a9f4f2ac08d96afc6
Parent: 72ff528
Committed by GitHub <noreply@github.com> on 6/9/2023, 7:39:59 AM