ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-24 00:19:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding IQ5_KS - 5.25 bpw quants (#422)

Browse Source 
* 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>
This commit is contained in:
Kawrakow
2025-05-15 16:02:39 +03:00
committed by GitHub
parent 17d721820a
commit 90e53a0b8b
20 changed files with 848 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -425,6 +425,7 @@ extern "C" {
GGML_TYPE_Q8_KR8 = 149,
GGML_TYPE_Q8_K128 = 150,
GGML_TYPE_Q8_KV = 151,
GGML_TYPE_IQ5_KS = 152,
GGML_TYPE_Q4_0_R8 = 202,
GGML_TYPE_Q5_0_R4 = 206,
@@ -512,6 +513,7 @@ extern "C" {
GGML_FTYPE_MOSTLY_IQ2_KS = 138, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ4_KSS = 139, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_KV = 140, // except 1d tensors
GGML_FTYPE_MOSTLY_IQ5_KS = 141, // except 1d tensors
//
GGML_FTYPE_MOSTLY_Q4_0_R8 = 202, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_0_R8 = 207, // except 1d tensors