More quantize support #60

Job	Run time
macOS-latest-cmake-ios	50s
macOS-latest-cmake-tvos	1m 30s
macOS-latest-cmake	2m 54s
macOS-latest-make	44s
ubuntu-focal-make	13s
macOS-latest-swift (generic/platform=macOS)	1m 11s
macOS-latest-swift (generic/platform=iOS)	59s
ubuntu-latest-cmake	1m 18s
macOS-latest-swift (generic/platform=tvOS)	29s
ubuntu-latest-cmake-mpi (mpich)	1m 30s
ubuntu-latest-cmake-mpi (libopenmpi-dev)	1m 34s
ubuntu-latest-cmake-sanitizer (ADDRESS, Debug)	3m 51s
windows-latest-cmake (noavx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_A...	2s
windows-latest-cmake-cublas (12.2.0, cublas)	17m 21s
windows-latest-cmake (avx2, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON)	1m 31s
windows-latest-cmake-cublas (11.7.1, cublas)	17m 29s
ubuntu-latest-cmake-sanitizer (ADDRESS, Release)	3m 21s
windows-latest-cmake (avx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SH...	1m 34s
ubuntu-latest-cmake-sanitizer (THREAD, Debug)	8m 5s
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...	1m 32s
ubuntu-latest-cmake-sanitizer (THREAD, Release)	4m 50s
windows-latest-cmake (clblast, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBU...	1m 19s
ubuntu-latest-cmake-sanitizer (UNDEFINED, Debug)	3m 35s
windows-latest-cmake (openblas, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUIL...	11s
ubuntu-latest-cmake-sanitizer (UNDEFINED, Release)	3m 19s
release	0s
	1h 21m 12s

Provide feedback