tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix token duplication when streaming with stop strings (#10997)

Browse Source
This commit is contained in:
Alexey Parfenov
2024-12-28 15:08:54 +00:00
committed by GitHub
parent d79d8f39b4
commit 16cdce7b68
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -1856,6 +1856,8 @@ struct server_context {
result.text_to_send = slot.generated_text.substr(pos, std::string::npos); result.text_to_send = slot.generated_text.substr(pos, std::string::npos);
slot.n_sent_text += result.text_to_send.size(); slot.n_sent_text += result.text_to_send.size();
// add the token to slot queue and cache // add the token to slot queue and cache
} else {
result.text_to_send = "";
} }
slot.add_token(result); slot.add_token(result);