mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-30 03:11:51 +00:00
Fused mul + multi_add op (#858)
* Adding fused mul+multi_add + CPU implementation * fused mul+multi_add: CUDA * fused mul+multi_add: command line argument to disable it --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
@@ -33,6 +33,7 @@ struct llama_cparams {
|
||||
bool fused_moe_up_gate;
|
||||
bool grouped_expert_routing;
|
||||
bool fused_up_gate;
|
||||
bool fused_mmad;
|
||||
int min_experts;
|
||||
float thresh_experts;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user