llama.cpp/ggml
Jeff Bolz 61bde8e21f
vulkan: Reduce temporary memory usage for TOP_K (#17623)
- Compute row size for the temp buffer based on the output of the first pass.
- Update shader addressing math to use the output row size
- Pass the output row size as "ncols_output", what used to be "ncols_output" is now "k"

For the common case of K=40 and src0=(200000,1,1,1), this reduces the temporary buffer
from about 3.2MB to 500KB.
2025-12-02 19:22:04 +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: LFM2-VL fixes (#17577) 2025-11-30 21:57:31 +01:00
src vulkan: Reduce temporary memory usage for TOP_K (#17623) 2025-12-02 19:22:04 +01:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt cmake : add utf8 compilation options for msvc (#17682) 2025-12-02 19:50:57 +02:00