ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-22 15:39:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hadamard transforms for K-cache - CPU only (#1033)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-12-04 06:51:11 +01:00
committed by GitHub
parent 0581f90c0f
commit 18fdd80eaf
13 changed files with 155 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -440,6 +440,7 @@ extern "C" {
int min_experts;
float thresh_experts;
bool only_active_experts;
bool k_cache_hadamard; // if true, apply Hadamard transfrom to K-cache
// Abort callback
// if it returns true, execution of llama_decode() will be aborted