ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-25 17:09:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding q8_KV - Basics + AVX2 gemm/gemv

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-02-17 10:55:47 +02:00
parent 047ba895bb
commit 538876471b
9 changed files with 289 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -180,6 +180,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_IQ3_KL = 146, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_KS = 147, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_KSS = 148, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_KV = 149, // except 1d tensors
//
LLAMA_FTYPE_MOSTLY_Q4_0_R8 = 202, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q8_0_R8 = 207, // except 1d tensors