CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : purge slots one by one

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-23 14:58:07 +03:00
parent 3e58ebe70f
commit f7a6b7d5df
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/server.cpp
View File

@@ -2731,6 +2731,9 @@ struct server_context {
slot.prompt.tokens.clear(); slot.prompt.tokens.clear();
res = true; res = true;
// purge slots one by one
break;
} }
} }