CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : bring back timings_per_token (#15879)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2025-09-08 21:50:05 +07:00
committed by GitHub
parent b0d52998b9
commit 56920f5665
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tools/server/server.cpp
View File

@@ -308,6 +308,7 @@ struct server_task {
// enabling this will output extra debug information in the HTTP responses from the server
params.verbose = params_base.verbosity > 9;
params.timings_per_token = json_value(data, "timings_per_token", false);
params.stream = json_value(data, "stream", false);
params.cache_prompt = json_value(data, "cache_prompt", true);