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
b10995
llama.cpp/ggml
T
History
SG-Amadeus d4365d9554 vulkan: make MUL_MAT_ID BN/2 tail unconditional (#28923) 
Use BN/2 as the default for BNover2 and as the disabled fallback for BNover4, and remove the enable gate from the MUL_MAT_ID BN/2 branch. The BN/4 branch remains gated by enable_smaller_matrices, while the p.N path is unchanged.
2026-09-16 08:45:44 +02:00
..
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
rpc : hash-cache only weights (#28789)
2026-09-15 14:50:20 +03:00
src
vulkan: make MUL_MAT_ID BN/2 tail unconditional (#28923)
2026-09-16 08:45:44 +02:00
.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