llama.cpp/ggml
Jeff Bolz 1fe00296f5
vulkan: fuse adds (#15252)
* vulkan: fuse adds

Fuse adds that have the same shape, which are common in MoE models.
It will currently fuse up to 6 adds, because we assume no more than
8 descriptors per dispatch. But this could be changed.

* check runtimeDescriptorArray feature

* disable multi_add for Intel due to likely driver bug
2025-08-16 11:48:22 -05:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00
src vulkan: fuse adds (#15252) 2025-08-16 11:48:22 -05:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00