upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-25 07:27:30 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
b11043
llama.cpp/ggml
T
History
Todor Boinovski 18a04f09c2 hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539) 
Allow HMX flash-attention to run with head_dim not a multiple of 64
(e.g. SigLIP head_dim=72), by operating on DK/DV rounded up to 64 with
zero-filled tail lanes.
2026-09-18 13:15:08 -07:00
..
cmake
CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)
2026-09-09 12:50:08 +02:00
include
[SYCL] Fix function signature for ggml_backend_sycl_split_buffer_type (#28981)
2026-09-16 22:15:47 -04:00
src
hexagon: HMX flash-attention head_dim padding (support DK=DV=72) (#26539)
2026-09-18 13:15:08 -07:00
.gitignore
vulkan : cmake integration (#8119)
2024-07-13 18:12:39 +02:00
CMakeLists.txt
ggml : bump version to 0.24.0 (ggml/1627)
2026-09-14 16:45:33 +03:00