ggml : refactor llamafile_sgemm PPC code (llama/14673)

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317)

llamafile : support s390x SIMD instruction set (llama/14273)

llama : add thread safety test (llama/14035)

ggml : Enable MMA for BF16 in llamafile_sgemm (llama/13148)

llamafile : ppc64le GEMV forwarding for FP32. (llama/12594)

llamafile : ppc64le MMA implementation for Q4_0. (llama/12489)

llamafile: use member variable instead of constant for iq4nlt (llama/11780)

llamafile : ppc64le MMA INT8 implementation (llama/10912)

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

ggml : more perfo with llamafile tinyblas on x86_64 (llama/10714)

ggml : fix arm build (llama/10890)

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

llamafile : fix include path (llama/0)

ggml : build backends as libraries (llama/10256)