More quantize support #61

Job	Run time
macOS-latest-cmake-ios	1m 15s
macOS-latest-cmake-tvos	53s
macOS-latest-cmake	2m 0s
macOS-latest-make	28s
macOS-latest-swift (generic/platform=macOS)	40s
macOS-latest-swift (generic/platform=iOS)	51s
ubuntu-latest-cmake	1m 19s
macOS-latest-swift (generic/platform=tvOS)	49s
ubuntu-focal-make	14s
ubuntu-latest-cmake-mpi (mpich)	1m 27s
ubuntu-latest-cmake-mpi (libopenmpi-dev)	1m 28s
ubuntu-latest-cmake-sanitizer (ADDRESS, Debug)	3m 38s
windows-latest-cmake (noavx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_A...	1m 10s
ubuntu-latest-cmake-sanitizer (ADDRESS, Release)	3m 21s
windows-latest-cmake-cublas (12.2.0, cublas)	11m 54s
windows-latest-cmake (avx2, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON)	2m 1s
ubuntu-latest-cmake-sanitizer (THREAD, Debug)	7m 48s
windows-latest-cmake (avx, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SH...	2m 1s
windows-latest-cmake-cublas (11.7.1, cublas)	12m 1s
ubuntu-latest-cmake-sanitizer (THREAD, Release)	4m 49s
windows-latest-cmake (avx512, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUIL...	1m 20s
ubuntu-latest-cmake-sanitizer (UNDEFINED, Debug)	3m 8s
windows-latest-cmake (clblast, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBU...	1m 12s
ubuntu-latest-cmake-sanitizer (UNDEFINED, Release)	3m 23s
windows-latest-cmake (openblas, -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUIL...	58s
release	0s
	1h 10m 8s

Provide feedback