ik_llama_opt/ggml
Kawrakow 90e53a0b8b Adding IQ5_KS - 5.25 bpw quants (#422)
* iq5_ks: basics

* iq5_ks: quantize

* iq5_ks: CUDA dequantize works

* iq5_ks: dot product works on CUDA

* iq5_ks: MMQ works

* iq5_ks: Zen4

* iq5_ks: AVX2

But is is not quite right, just like iq4_k, iq5_k, iq6_k, iq4_ks.
All these need fixing on AVX2.

* iq5_ks: NEON

* iq5_ks: Metal dequantize

* iq5_ks: Metal dot product

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-05-15 16:02:39 +03:00
..
cmake
include Adding IQ5_KS - 5.25 bpw quants (#422) 2025-05-15 16:02:39 +03:00
src Adding IQ5_KS - 5.25 bpw quants (#422) 2025-05-15 16:02:39 +03:00
.gitignore
CMakeLists.txt Compile time option to use bf16 for qunts without MMQ kernels (#261) 2025-03-18 07:37:10 +01:00