tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : added --no-prefill-assistant flag (#13608)

Browse Source 
* added no-prefill-assistant flag

* reworded documentation comment

* updated server README.md
This commit is contained in:
Isaac McFadyen
2025-05-17 17:59:48 -04:00
committed by GitHub
parent e3a7cf6c5b
commit 6a2bc8bfb7
5 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server.cpp
View File

@ -4348,6 +4348,7 @@ int main(int argc, char ** argv) {
json data = oaicompat_completion_params_parse(
body,
params.use_jinja,
params.prefill_assistant,
params.reasoning_format,
ctx_server.chat_templates.get(),
ctx_server.mctx,
@ -4369,6 +4370,7 @@ int main(int argc, char ** argv) {
json data = oaicompat_completion_params_parse(
body,
params.use_jinja,
params.prefill_assistant,
params.reasoning_format,
ctx_server.chat_templates.get(),
ctx_server.mctx,