ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 08:04:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

IQ4_XS_R4 (#123)

Browse Source 
* Adding iq4_xs_r4

This is a 1st working version on Zen4.
We get PP-512(LLaMA-3.1-8B) = 226 t/s, so 16% slower
than iq4_nl_x4.

* iq4_xs_r4: WIP

* iq4_xs_r4: Use AVX2 version for matrix x vector on Zen4

* iq4_xs_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 115.6 t/s on M2-Max,
up from 68.2 t/s for iq4_xs!

* DRY

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-04 15:20:07 +01:00
committed by GitHub
parent bb699e1e6b
commit 9119023a4b
10 changed files with 421 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -184,6 +184,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q8_0_R4 = 207, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_0_R4 = 208, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_NL_X4 = 225, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 235, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file