Model techniques map
Techniquesinference & servinginference scheduling

specific method · filed under inference & serving

Envoy-based proxy with custom orchestrator

A serving setup that uses an Envoy proxy and custom orchestrator for session management and KV-cache-aware routing across deployments.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

To manage traffic across Atlas deployments we run an Envoy-based proxy paired with a custom orchestrator that owns session management and routing across the fleet, optimizing KV-cache utilization during agentic reinforcement learning.

usedinference servingPoolside

Filed alongside

Other methods under inference & serving :: inference scheduling.