ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 19:01:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Offload only activated experts to the GPU (#698)

Browse Source 
* Offload only activated experts

* This seems to do the trick for -fmoe

* Do not recalculate activated expers for fused up/gate

* Log out of bounds access details

* Add a command line argument

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-09-04 12:22:30 +02:00
committed by GitHub
parent 06cc7c6894
commit 0c15494c30
8 changed files with 155 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/llama.h
View File

@@ -424,6 +424,7 @@ extern "C" {
bool fused_up_gate; // whether to use fused up/gate op [EXPERIMENTAL]
int min_experts;
float thresh_experts;
bool only_active_experts;
// Abort callback
// if it returns true, execution of llama_decode() will be aborted