ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (llama/12154)

HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (llama/12032)

CUDA: compress mode option and default to size (llama/12029)

cmake: Fix ggml backend dependencies and installation (llama/11818)

Told cmake to install ggml-cpp.h as a public header file. (ggml/1126)

ggml-cpu: Support s390x SIMD Instruction Set (llama/12019)

CUDA: app option to compile without FlashAttention (llama/12025)

ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390)

cmake: Add ability to pass in GGML_BUILD_NUMBER (ggml/1096)

cmake: add ggml find package (llama/11369)

Hip: disable VMM on hip as it seams that it dosent work in some configurations (llama/11420)

hip : Add hipGraph and VMM support to ROCM (llama/11362)

cmake : avoid -march=native when reproducible build is wanted (llama/11366)

fix: ggml: fix vulkan-shaders-gen build (llama/10448)

GGUF: C++ refactor, backend support, misc fixes (llama/11030)

ggml : do not install metal source when embed library (ggml/1054)

ggml : fix arm build (llama/10890)

Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (llama/10693)

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)

ggml : add predefined list of CPU backend variants to build (llama/10626)

ggml : move AMX to the CPU backend (llama/10570)

ggml : add support for dynamic loading of backends (llama/10469)

add cmake rvv support (llama/10411)

ggml : sync resolve (skip) (#0)

Add required ggml-base and backend libs to cmake pkg (llama/10407)

sycl : Add option to set the SYCL architecture for all targets (llama/10266)

CUDA: remove DMMV, consolidate F16 mult mat vec (llama/10318)

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (llama/9921)

ggml : build backends as libraries (llama/10256)

metal : opt-in compile flag for BF16 (llama/10218)

ggml : add ggml-cpu.h to the public headers (llama/10204)

add amx kernel for gemm (llama/8998)

cmake : do not hide GGML options + rename option (llama/9465)

Improve Vulkan shader build system (llama/9239)

sync : vulkan (skip) (llama/0)

cmake : remove unused option GGML_CURL (llama/9011)

cann: update cmake (llama/8765)

feat: Support Moore Threads GPU (llama/8383)

cmake : install all ggml public headers (llama/8480)

ggml : move sgemm sources to llamafile subfolder (llama/8394)

cmake : only enable GGML_NATIVE and x86 flags if not crosscompiling (ggml/885)

ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (llama/8140)

whisper : reorganize source code + improve CMake (#2256)