Skip to content

Releases: dalong0514/llama.cpp

b4687

Choose a tag to compare

@github-actions github-actions released this 11 Feb 07:58
b9ab0a4
CUDA: use arch list for compatibility check (#11775)

* CUDA: use arch list for feature availability check

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>

b2186

Choose a tag to compare

@github-actions github-actions released this 19 Feb 02:08
a0c2dad
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

Choose a tag to compare

@github-actions github-actions released this 08 Feb 02:23
c4fbb67
CMAKE_OSX_ARCHITECTURES for MacOS cross compilation (#5393)

Co-authored-by: Jared Van Bortel <jared@nomic.ai>

b2078

Choose a tag to compare

@github-actions github-actions released this 06 Feb 12:01
8a79c59
server : include total "num_slots" in props endpoint (#5349)

b1960

Choose a tag to compare

@github-actions github-actions released this 24 Jan 07:47
26d6076
metal : disable support for MUL_MAT F32 x F16

b1742

Choose a tag to compare

@github-actions github-actions released this 01 Jan 09:04
flake.lock: update

to a commit recently cached by nixpkgs-cuda-ci