git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-03-01 21:00:04 +01:00
Code Issues Packages Projects Releases Wiki Activity

server: Mirroring /v1/responses to /responses to match /v1/chat/completions pattern (#19873)

Browse Source
This commit is contained in:
Sami Kama 2026-02-27 08:44:42 -08:00 committed by GitHub
parent 8d3b962f47
commit 5596a35791
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tools/server/server.cpp
View File

@ -178,6 +178,7 @@ int main(int argc, char ** argv) {
ctx_http.post("/v1/chat/completions", ex_wrapper(routes.post_chat_completions));
ctx_http.post("/api/chat", ex_wrapper(routes.post_chat_completions)); // ollama specific endpoint
ctx_http.post("/v1/responses", ex_wrapper(routes.post_responses_oai));
ctx_http.post("/responses", ex_wrapper(routes.post_responses_oai));
ctx_http.post("/v1/messages", ex_wrapper(routes.post_anthropic_messages)); // anthropic messages API
ctx_http.post("/v1/messages/count_tokens", ex_wrapper(routes.post_anthropic_count_tokens)); // anthropic token counting
ctx_http.post("/infill", ex_wrapper(routes.post_infill));