0 0 0 C++

Vulkan Embedding Fix (#7360)

* Fix empty Vulkan host buffers

Add fp32 fp16 matmul shader

Fix matmul shader alignment

* Remove deprecated tensor->backend uses

* Fix Vulkan validation errors on embedding models with no offloaded layers

* Fix Vulkan llava segfault when not offloading layers

0cc4m committed 2y ago

f030ec1f7a72aa825b2104823946551b9ec5dfc1

Parent: e4e6f67

Committed by GitHub <noreply@github.com> on 5/19/2024, 3:19:53 PM