This website requires JavaScript.
Explore
Help
Sign In
nikola
/
llama_cpp
Watch
1
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
27
Packages
Projects
Releases
Wiki
Activity
Files
b14e3fb90ca8c760f4254ddc9aa7845ebbdb2edf
llama_cpp
/
ggml
/
src
/
ggml-opencl
T
History
lhez
and
GitHub
51571722aa
opencl: optimize mul_mat_f16_f32_l4 for decode (
#24504
)
2026-06-16 23:21:26 -07:00
..
kernels
opencl: optimize mul_mat_f16_f32_l4 for decode (
#24504
)
2026-06-16 23:21:26 -07:00
CMakeLists.txt
opencl: add q5_0/q5_1 gemm and gemv kernels for Adreno (
#24319
)
2026-06-11 21:43:09 -07:00
ggml-opencl.cpp
opencl: optimize mul_mat_f16_f32_l4 for decode (
#24504
)
2026-06-16 23:21:26 -07:00