REST Endpoints¶
The REST endpoints are based on KServe’s v2 specification. Additional endpoints are driven by community adoption.
Health¶
GET
v2/health/live
: Check if the server is liveGET
v2/health/ready
: Check if the server is ready for inference requestsGET
v2/models/{model}/ready
: Check if a particular model is ready for inference requests
Metadata¶
GET
v2
: Get Xilinx Inference Server’s metadataGET
v2/hardware
: Get a string describing the number and type of kernels that are availableGET
v2/models/{model}
: Get model metadata
Inference¶
POST
v2/repository/models/{model}/load
: Load a model. The HTML body in the response contains the endpoint to use for this modelPOST
v2/repository/models/{model}/unload
: Unload a modelPOST
v2/models/{model}/infer
: Make an inference request to a particular model
Observation¶
GET
metrics
: Get Prometheus metrics