koboldcpp/ggml
Jeff Bolz 7799d31e68
vulkan: optimize conv2d and implement coopmat1 support (#22620)
* vulkan: add CONV_SHAPE_64x128 for medium-K conv2d

* vulkan: skip conv2d bounds checks when shapes align with tile sizes

* vulkan: use WG_SIZE=128 for CONV_SHAPE_64x32 conv2d

* vulkan: stage cm2 conv2d accumulator through shmem before global store

* vulkan: add coopmat1 conv2d path

* fallback when using too much shared memory. clean up comments

* Require 16x16x16 and subgroup size 32 or 64

* check whether shared memory is sufficient before overwriting conv2d params with coopmat1 values
2026-05-26 15:48:05 +02:00
..
cmake ggml : Parallelize quant LUT init (#23595) 2026-05-25 10:15:46 +03:00
include ggml.h: correct ggml_silu_back arg docstring (a=dy, b=x) (ggml/1500) 2026-05-25 12:38:01 +03:00
src vulkan: optimize conv2d and implement coopmat1 support (#22620) 2026-05-26 15:48:05 +02:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml : bump version to 0.13.0 (ggml/1510) 2026-05-25 12:43:27 +03:00