sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 12:34:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: support Vertex AI compatible API

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-04-30 11:55:13 +02:00
parent 19821178be
commit bfc135fee2
4 changed files with 227 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/server.cpp
View File

@@ -204,6 +204,10 @@ int main(int argc, char ** argv) {
// Save & load slots
ctx_http.get ("/slots", ex_wrapper(routes.get_slots));
ctx_http.post("/slots/:id_slot", ex_wrapper(routes.post_slots));
// Vertex AI Prediction protocol endpoint (AIP_PREDICT_ROUTE, or /predict by default)
ctx_http.register_vertexai();
// CORS proxy (EXPERIMENTAL, only used by the Web UI for MCP)
if (params.webui_mcp_proxy) {
SRV_WRN("%s", "-----------------\n");