ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Q3_K_R4 (#134)

Browse Source 
* q3_k_r4: Zen4 works, but not as good as it should be

238 t/s, so sloghtly slower than q6_k_r4.

* q3_k_r4: NEON

We get PP-512(LLaMA-3.1-8B) = 106.9 t/s.
This is 1.93X faster than q3_K_S!

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-12-11 11:19:00 +01:00
committed by GitHub
parent e78e47b857
commit 4872f2f57e
10 changed files with 356 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -183,6 +183,7 @@ 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_Q3_K_R4 = 211, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q4_K_R4 = 214, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q5_K_R4 = 216, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_K_R4 = 218, // except 1d tensors