Merge branch 'master' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	Package.swift
#	README.md
#	ggml-cuda.cu
#	llama.cpp
#	llama.h
#	scripts/sync-ggml.sh
#	tests/CMakeLists.txt

expose.h

@@ -28,7 +28,6 @@ struct load_model_inputs
     const int blasthreads;
     const int max_context_length;
     const int batch_size;
-    const bool f16_kv;
     const bool low_vram;
     const bool use_mmq;
     const char * executable_path;