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

Update examples/server/server.cpp

Browse source 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Maximilian Winter 2024-01-27 11:47:27 +01:00 • committed by GitHub
parent 67096a3539
commit d56cecc2cd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/server/server.cpp
View file

@ -184,8 +184,7 @@ struct llama_client_slot
struct llama_sampling_params sparams;
llama_sampling_context *ctx_sampling = nullptr;
int ga_i = 0; // group-attention state
int32_t ga_i = 0; // group-attention state
int32_t ga_n = 1; // group-attention factor
int32_t ga_w = 512; // group-attention width