Protocol
Triton Inference Protocol
KServe · V2 inference protocol
Lab ready Full lab
HTTP/gRPC model-inference APIs popularized by Triton/KServe V2: readiness/liveness, infer, and model-repository control. Tensor contents, datatypes, and shared-memory extensions dominate latency. It standardizes serving regardless of the backend framework.
Domains
Layers
Tags
inferenceservingtensorsml
Related protocols
gRPC
Lab readyRPC framework on HTTP/2 with protobuf stubs, streaming RPCs, deadlines, and metadata. Widely used as the control plane for ML serving, mi…
aiinternet
HTTP/2
Lab readyMultiplexed binary framing over a single TLS/TCP connection with streams, HPACK headers, and flow-control windows. It underpins gRPC and …
internetai
Arrow Flight
Lab readygRPC protocol for bulk Apache Arrow record-batch transfer with DoGet/DoPut and FlightDescriptors. Columnar data moves with minimal copies…
aiinternet