tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix EOS token detection with disabled cache (#5938)

Browse Source
This commit is contained in:
Georgi Gerganov
2024-03-08 12:40:02 +02:00
committed by GitHub
parent 581ed5c4fe
commit af37fd8b30
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -1123,7 +1123,7 @@ struct server_context {
});
}
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;