ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Vulkan: Add DP4A MMQ and Q8_1 quantization shader (#12135)

Browse source 
* Vulkan: Add DP4A MMQ and Q8_1 quantization shader

* Add q4_0 x q8_1 matrix matrix multiplication support

* Vulkan: Add int8 coopmat MMQ support

* Vulkan: Add q4_1, q5_0 and q5_1 quants, improve integer dot code

* Add GL_EXT_integer_dot_product check

* Remove ggml changes, fix mmq pipeline picker

* Remove ggml changes, restore Intel coopmat behaviour

* Fix glsl compile attempt when integer vec dot is not supported

* Remove redundant code, use non-saturating integer dot, enable all matmul sizes for mmq

* Remove redundant comment

* Fix integer dot check

* Fix compile issue with unsupported int dot glslc

* Update Windows build Vulkan SDK version
This commit is contained in:
0cc4m 2025-03-31 14:37:01 +02:00 • committed by GitHub
parent 1790e73157
commit a8a1f33567
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 1146 additions and 95 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/build.yml vendored
View file

@ -803,7 +803,7 @@ jobs:
env:
OPENBLAS_VERSION: 0.3.23
SDE_VERSION: 9.33.0-2024-01-07
VULKAN_VERSION: 1.4.304.1
VULKAN_VERSION: 1.4.309.0
strategy:
matrix: