Mirror
/
LocalAI
mirror of https://github.com/mudler/LocalAI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix(llama.cpp): fix eos without cache

This commit is contained in:
Ettore Di Giacinto 2024-03-18 12:14:16 +01:00
parent b790fca180
commit 495191a54a
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backend/cpp/llama/grpc-server.cpp
View File

@ -1084,7 +1084,7 @@ struct llama_server_context
slot.has_next_token = false;
}
if (!slot.cache_tokens.empty() && result.tok == llama_token_eos(model))
if (result.tok == llama_token_eos(model))
{
slot.stopped_eos = true;
slot.has_next_token = false;