Triton Inference Server

docker run --rm -p8000:8000 -p8001:8001 -p8002:8002 
-v C:\Users\j\.models:/models 
nvcr.io/nvidia/tritonserver:25.05-trtllm-python-py3 tritonserver 
--model-repository=/models

curl -v localhost:8000/v2/health/ready

Docker catalog here. Quick start here.