Morph MORPH
SIGN IN SIGN UP
dhruvhead / llama.cpp UNCLAIMED
0 0 0 C++

Vulkan Mixture of Experts (MoE) support (#7628)

* Finish Vulkan mul_mat_id implementation

* Add Vulkan sum_rows and div ops

* Fix MUL_MAT_ID matrix matrix shader

* Fix MUL_MAT_ID matrix vector shader dispatch size

* Fix MUL_MAT_ID matrix vector shader and dispatch code

* Update Vulkan CPU offload for MUL_MAT_ID

* Fix crash when using split mode none and setting a main GPU
0
0cc4m committed
3d7ebf63123b8652fb7bbecef7ba731202309901
Parent: a10cda5
Committed by GitHub <noreply@github.com> on 6/3/2024, 8:59:14 AM