Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-09 06:19:04 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
330c3d2d21b55bca5517db7d2eea2ea8f131df4a
llama.cpp/ggml/src/ggml-vulkan
T
History
Jeff Bolz 330c3d2d21 vulkan: optimize mul_mat_id loading row ids into shared memory (#15427) 
- Spread the work across the whole workgroup. Using more threads seems to
far outweigh the synchronization overhead.
- Specialize the code for when the division is by a power of two.
2025-08-23 08:31:54 +02:00
..
cmake
cmake: fix ggml-shaders-gen compiler paths containing spaces (#12747)
2025-04-04 10:12:40 -03:00
vulkan-shaders
vulkan: optimize mul_mat_id loading row ids into shared memory (#15427)
2025-08-23 08:31:54 +02:00
CMakeLists.txt
vulkan: Fix GGML_VULKAN_SHADER_DEBUG_INFO (#14427)
2025-06-27 22:35:30 -05:00
ggml-vulkan.cpp
vulkan: optimize mul_mat_id loading row ids into shared memory (#15427)
2025-08-23 08:31:54 +02:00