vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update server.cpp

Browse source
This commit is contained in:
Maximilian Winter 2024-01-27 14:15:36 +01:00
parent 826e6dcad9
commit f7c0e043de
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/server.cpp
View file

@ -184,8 +184,8 @@ struct llama_client_slot
struct llama_sampling_params sparams;
llama_sampling_context *ctx_sampling = nullptr;
int32_t ga_i = 0; // group-attention state
int32_t ga_n = 1; // group-attention factor
int32_t ga_i = 0; // group-attention state
int32_t ga_n = 1;// group-attention factor
int32_t ga_w = 512; // group-attention width
int32_t n_past_se = 0; // self-extend