Releases: dalong0514/llama.cpp
Releases · dalong0514/llama.cpp
Release list
b4687
b2186
build : pass all warning flags to nvcc via -Xcompiler (#5570) * build : pass all warning flags to nvcc via -Xcompiler * make : fix apparent mis-merge from #3952 * make : fix incorrect GF_CC_VER for CUDA host compiler
b2096
CMAKE_OSX_ARCHITECTURES for MacOS cross compilation (#5393) Co-authored-by: Jared Van Bortel <jared@nomic.ai>
b2078
server : include total "num_slots" in props endpoint (#5349)
b1960
metal : disable support for MUL_MAT F32 x F16
b1742
flake.lock: update to a commit recently cached by nixpkgs-cuda-ci