mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-09 04:30:33 +00:00
40f3aafc45
* server: add "X-Accel-Buffering": "no" header to streaming endpoints This header tells Nginx (as a reverse proxy) to NOT buffer responses. (only affects streaming endpoints) Without it, Nginx will break streaming with certain applications (notably the Pi coding harness).