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

Turn on graph reuse by default (#1094)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-12-27 08:27:16 +01:00
committed by GitHub
parent 519405dc97
commit f878adbe90
3 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.h
View File

@@ -265,7 +265,7 @@ struct gpt_params {
bool fused_mmad = true; // fused mul+multi_add op
bool grouped_expert_routing = false; // if to use grouped expert routing (BailingMoeV2 arch)
bool rope_cache = false; // if to use RoPE cache (for supported models)
bool graph_reuse = false; // if to reuse compute graphs
bool graph_reuse = true; // if to reuse compute graphs
int min_experts = -1;
float thresh_experts = 0;