biondizzle 7fb373fdfc Add haproxy proxy: /metrics returns 200 empty, everything else proxies to SGLang ...

SGLang now runs on port+1, haproxy binds the original vLLM port.
haproxy serves a stub /metrics endpoint (200, empty body) and
passes all other traffic through to SGLang via raw TCP proxy.

2026-04-12 17:09:58 +00:00

1.8 KiB

Raw Permalink Blame History

View Raw