Releases: mehendarkarprajwal/llama.cpp
Releases · mehendarkarprajwal/llama.cpp
b6780
b6779
CANN: format code using .clang-format (#15863) This commit applies .clang-format rules to all source files under the ggml-cann directory to ensure consistent coding style and readability. The .clang-format option `SortIncludes: false` has been set to disable automatic reordering of include directives. No functional changes are introduced. Co-authored-by: hipudding <[email protected]>
b6721
Dont define XOPENSOURCE on AIX
b6720
ci: add ARM64 Kleidiai build and test support (#16462)
b5537
Undefine hz on AIX
b5536
gguf-py : add support for sub_type (in arrays) in GGUFWriter add_key_…
b5486
tests : improve UGM tokenizer test coverage (#13773)
b5124
Define cache directory on AIX
b5123
vulkan: use aligned loads for flash attention mask (#12853) Rewrite the stride logic for the mask tensor in the FA shader to force the stride to be aligned, to allow using more efficient loads.
b5081
Including limits header file on AIX