4 Commits
Author SHA1 Message Date
geohot 29f7d03d43 k5 support 2025-07-28 19:11:27 -07:00
geohot ad1a2a68d5 add amd kernel 4 2025-07-28 16:14:11 -07:00
George HotzandGitHub b0dc97d1f7 write out kernel 3 in uops (#11352)
* write out kernel 3 in uops

* matmul is correct

* gemm passes spec

* bugfix to match speed

* cleanups
2025-07-23 17:32:38 -07:00
George HotzandGitHub d67c8e7b42 local metal on metal in uop syntax (#11185)
* local metal on metal in uop syntax

* TODO: just put the axis_info in the kernelinfo

* local

* amd_matmul works @ 28 TFLOPS

* clean up matmul

* kernel8 works

* remove that

* locals

* axistype innovation

* work

* cleanup

* kernel3 regs

* cleanup kernel3

* work

* why is it broken

* no beam

* reenable

* permutes
2025-07-12 16:31:19 -07:00