ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 16:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Q5_0_R4 (#121)

Browse Source 
* Adding q5_0_r4

We get PP-512(LLaMA-3.1-8B) = 256.7 t/s on a Ryzen-7950X.
We even get TG-128 improvement to 11.7 t/s from 11.1 t/s.

* q5_0_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 99.6 t/s on M2-Max,
up from 71.0 t/s for Q5_0. The difference to mainline llama.cpp
is no longer funny: they get 26.5 t/s for Q5_0.

For TG, we are nor able to fully saturate memory bandwidth
and arrive at 22.1 t/s @ 8 threads. Mainline llama.cpp gets
20.6 t/s for Q5_0.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-03 12:59:22 +01:00
committed by GitHub
parent ccec00939a
commit c5bf589367
10 changed files with 383 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -182,6 +182,7 @@ extern "C" {
//
LLAMA_FTYPE_MOSTLY_Q4_0_R4 = 202, // except 1d tensors
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_GUESSED = 1024, // not specified in the model file