Implement Inference Extension#4091

Merged

ciarams87 merged 11 commits intomainfrom

feat/inference-extension

Oct 17, 2025

Commits on Oct 17, 2025

Basic NJS module to extract model name (#3877)

sjberman
authored and
ciarams87
committed
Watch InferencePools and configure nginx (#3894)

sjberman
authored and
ciarams87
committed
Add golang shim for comms with EPP (#3930)

sjberman
authored and
ciarams87
committed
Query EPP and proxy AI traffic (#3942)

sjberman
authored and
ciarams87
committed
Adds status information to describe the state of Inference Pools (#3970)

salonichf5
authored and
ciarams87
committed
Update gateway inference extension proposal security considerations (#4006)

bjee19
authored and
ciarams87
committed
Add status to Inference Pools (#4005)

salonichf5
authored and
ciarams87
committed
Collect InferencePoolCount in telemetry (#4008)

bjee19
authored and
ciarams87
committed
rebase inference extension branch with main

salonichf5
authored and
ciarams87
committed
Add fix for inference pool status (#4088)

bjee19
authored and
ciarams87
committed
Update inference extension conformance tests (#4089)

salonichf5
authored and
ciarams87
committed