Kawrakow 67817fb5b9 IQ2_KS: 2.1875 bpw non-linear quantization (#85) ... * Experimenting * iq2k: Try make_qx_quants for the scale Slightly better for LLaMA-3.1, Gemma-2, slightly worse for Qwen2.5 * iq2k with make_qx_quants: adjust scale * iq2ks: basics * iq2_ks: CUDA works * iq2_ks: WIP * iq2_ks: WIP * iq2_ks: Zen4 * iq2_ks: AVX2 * iq2_ks: scalar dot product * iq2_ks: ARM_NEON * iq2_ks: Metal * iq2_ks: faster Metal LLaMA-3.1-8B: PP-512 = 475.22 ± 0.37 t/s TG-128 = 45.32 ± 0.03 t/s --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2024-10-13 13:34:30 +03:00
..
ggml-alloc.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-backend.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-blas.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-cann.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-cuda.h	Merge mainline - Aug 12 2024 (#17)	2024-08-12 15:14:32 +02:00
ggml-kompute.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-metal.h	Merge mainline - Aug 12 2024 (#17)	2024-08-12 15:14:32 +02:00
ggml-rpc.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-sycl.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml-vulkan.h	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
ggml.h	IQ2_KS: 2.1875 bpw non-linear quantization (#85)	2024-10-13 13:34:30 +03:00