]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: a6b3260)
server: add "X-Accel-Buffering": "no" header to streaming endpoints (#24774)
authorReguna <redacted>
Thu, 18 Jun 2026 20:01:24 +0000 (04:01 +0800)
committerGitHub <redacted>
Thu, 18 Jun 2026 20:01:24 +0000 (22:01 +0200)
commit40f3aafc45990c1646397c67d2bd3e8eff3f543e
tree46da1324b4afdb3b83b9f63f40a29069fbde54e1tree
parenta6b3260a4268d3c9931e0c47859fe4ff8f108bd9commit | diff
server: add "X-Accel-Buffering": "no" header to streaming endpoints (#24774)

* 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).
tools/server/server-http.cpp diff | blob | history
Packaging of ggml-org/llama.cpp