SGLang Sidecar
Experimental. The SGLang sidecar, launchers, packaging, and feature coverage can change without notice.
dynamo-sglang-sidecar is a CPU-only Dynamo worker that connects to SGLang’s
native gRPC service. It preserves the upstream engine process and argument
surface while using Dynamo for request handling and distributed serving. See
the Sidecar Backends page for the common
architecture.
Readiness
This table covers launch topology only. The SGLang feature matrix describes the in-process backend; sidecar feature parity is still under evaluation. See the SGLang sidecar README for current protocol details.
Launch Locally
From a Dynamo source checkout, build or install Dynamo so
dynamo-sglang-sidecar is on PATH. Install SGLang v0.5.16 or later, which
provides the native --grpc-port server option.
Start Dynamo’s local discovery services, then run the aggregated launcher:
To run separate prefill and decode engines on two GPUs:
Each launcher starts the Dynamo frontend, the SGLang engine process or processes, and the matching sidecar workers. It binds SGLang’s HTTP and native gRPC endpoints to loopback.
Verify the frontend:
Deploy on Kubernetes
No published sidecar image is available yet. Follow the
Kubernetes quick start
to build dynamo-sidecar, which contains all three engine-specific sidecar
executables. The SGLang manifests run dynamo-sglang-sidecar as the container
command and pair it with a stock upstream SGLang image. The source tree includes
aggregated
and
disaggregated
manifests.