llama.cpp/ggml
Jeff Bolz 2e76e01360
vulkan: fuse mul_mat+add and mul_mat_id+add_id (#16868)
* vulkan: fuse mul_mat+add and mul_mat_id+add_id

The fusion is only applied for the mat-vec mul paths.

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix 32b build

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2025-11-01 06:45:28 +01:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include model: add support for qwen3vl series (#16780) 2025-10-30 16:19:14 +01:00
src vulkan: fuse mul_mat+add and mul_mat_id+add_id (#16868) 2025-11-01 06:45:28 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2025-10-22 13:47:09 -07:00