ggml: initial IBM zDNN backend (llama/14975)

cmake: Add GGML_BACKEND_DIR option (llama/15074)

ggml: Add initial WebGPU backend (llama/14521)

sync : resolve conflicts (#0)

Implement GGML_CPU_ALL_VARIANTS for PowerPC (llama/14286)

ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258)

ggml: Add Android support for GGML_CPU_ALL_VARIANTS (llama/14206)

Implement GGML_CPU_ALL_VARIANTS for ARM (llama/14080)

llama : allow using mmap without PrefetchVirtualMemory, apply GGML_WIN_VER to llama.cpp sources (llama/14013)

Add in-build ggml::ggml ALIAS library (ggml/1260)

cmake: Guard GGML_CPU_ALL_VARIANTS by architecture (llama/13890)

cmake: Factor out CPU architecture detection (llama/13883)

ggml : install dynamic backends (ggml/1240)

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

whisper : install shared libs when using GGML_BACKEND_DL (#3195)

cmake : removed stdc++fs (#3097)

ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (llama/12871)

cmake : fix ccache conflict (llama/12522)

Fix build on Windows when ccache enabled (ggml/9954) (llama/9976)

Fix visionOS build and add CI (llama/12415)

cmake : enable building llama.cpp using system libggml (llama/12321)

cmake : fix undefined reference errors for std::filesystem in ggml (#12092) (llama/12094)

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

whisper : support GGML_BACKEND_DL (#2843)

`ci`: use sccache on windows instead of ccache (llama/11545)

cmake : don't fail on `GGML_CPU=OFF` (llama/11457)

cmake: add ggml find package (llama/11369)

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

ggml : fixes for AVXVNNI instruction set with MSVC and Clang (llama/11027)

ggml : use wstring for backend search paths (llama/10960)

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

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)

ggml : refactor online repacking (llama/10446)

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

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

cmake : enable warnings in llama (llama/10474)

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

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

ggml: new optimization interface (ggml/988)

cmake : restore CMakeLists.txt (llama/10256)

cmake : fix ppc64 check (#0)

ggml : optimize llamafile cpu matrix multiplication for ppc64le (llama/10156)

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

ggml : move CPU backend to a separate file (llama/10144)

llama : use smart pointers for ggml resources (llama/10117)

build: fix build error in Windows env with OneAPI setup (llama/10107)

kompute: add mul_mat_q4_k shader (llama/10097)

cmake : make it possible linking ggml as external lib (ggml/1003)

add amx kernel for gemm (llama/8998)

musa: add docker image support (llama/9685)