llama-cpp-sys-4 0.3.1

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6

// HMX operations compiled as a single translation unit.
// This allows interprocedural optimizations within HMX ops without requiring global HTP LTO.

#include "hmx-queue.c"
#include "hmx-matmul-ops.c"
#include "hmx-flash-attn-ops.c"