ggml : improve f16 acceleration for POWER9 ppc64le

ggml : barrier refactor + static functions

ggml : simplify the SIMD code (#324)

ggml : use vaddvq_f32 for slightly more efficient reduce

ggml : add f16 acceleration for POWER9 ppc64le

ggml : make consts static (#317)

minor : small code cleanups (#302)

Check for both __ARM_NEON and __ARM_FEATURE_FMA so that the project can be compiled for armv7a.

Add AVX,AVX2 support for ggml_vec_scale_f32

ggml : implement ggml_compute_forward_dup_f16() special cases

ggml : make more compatible with c99 (#262)

ggml : fix indentation

ggml : make compatible with c99 (#262)

Remove C++20 requirement (#257)

talk : talk with AI in the terminal

ggml : add alternative cblas_sgemm call

fix compilation on haiku

ggml : fix typo in previous commit

ggml : use macros to inline FP16 <-> FP32 conversions

ggml : add F16C CPU flag check

add fp16/fp32 convert intrinsics

ggml : remove inline specifier from fp16 <-> fp32 converters

ggml : fix the fix

ggml : fix cross-compile Linux -> Window with mingw (#168)

ggml: change inline ggml_fp16_to_fp32, ggml_fp16_t ggml_fp32_to_fp16

add AVX support

ggml : fix Windows build

Fix the Windows pthread_create shim

ggml : multi-thread the ggml_add operator

ggml : fix the check for NEON support (#7)

Cross compilation (#121)

Fixed sched_yield

Implemenated sched_yield function for Windows

ggml : fix barrier

ggml : fix thread-safety of ggml_init and ggml_free

Add OpenBLAS support

ggml : add system info functions

refactoring : move main + stream in examples + other stuff

wip : WASM 128-bit SIMD support

wip : initial WASM port

Add reference to FP16 repo

Correct implementation of FP16 GELU

Revert GELU change

Use Accelerate framework on Apple silicon

close #56 : build on FreeBSD

Building with MSVC

Add MinGW support

ref #11, #18, #26 : fix CACHE_LINE_SIZE constant

wip : rpi4 support

Flash + language support (ref #2)