Vulkan Bugfixes and Improvements (#7084)

Browse Source

* Modify mat mat mul shader for mul_mat_id, modify mat vec mul shaders for single call batch operation

* Further work towards MoE, disabled for now

* Disable MoE code (not ready yet), fix a number of bugs in shaders and Vulkan code

* Add softmax with f16 mask and pos buffer support

* Disable mul_mat_id shaders for now

* Fix flake8

* Fix validation errors caused by empty buffers on larger batch sizes

...

This commit is contained in:

0cc4m authored and GitHub committed 2024-05-09 20:39:54 +02:00

1 parent d46dbc76f8

commit befddd0f15

3 files changed

+43648 -34961

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

ggml-vulkan-shaders.hpp

+42182 -34544

File diff suppressed because it is too large. Load diff

ggml-vulkan.cpp

+925 -242

File diff suppressed because it is too large. Load diff

ggml_vk_generate_shaders.py

+541 -175

File diff suppressed because it is too large. Load diff