|
..
|
|
configure_serve_deployment
|
|
fault_tolerance
|
|
getting_started
|
|
grpc_proxy
|
|
http_guide
|
|
model_composition
|
|
monitoring
|
|
production_guide
|
|
app_builder.py
|
|
autoscale_model_comp_example.py
|
|
aws_neuron_core_inference_serve.py
|
|
aws_neuron_core_inference_serve_stable_diffusion.py
|
|
batching_guide.py
|
|
delayed_import.py
|
|
develop_and_deploy.py
|
|
distilbert.py
|
|
fake_email_creator.py
|
|
fake_email_creator.yaml
|
|
faker.py
|
|
fastapi_example.py
|
|
gradio-integration-parallel.py
|
|
gradio-integration.py
|
|
gradio-original.py
|
|
image_classifier_example.py
|
|
intel_gaudi_inference_client.py
|
|
intel_gaudi_inference_serve.py
|
|
intel_gaudi_inference_serve_deepspeed.py
|
|
key_concepts.py
|
|
load_shedding.py
|
|
local_dev.py
|
|
managing_deployments.py
|
|
multiplexed.py
|
|
object_detection.py
|
|
quickstart.py
|
|
quickstart_composed.py
|
|
requests_best_practices.py
|
|
resnet50_example.py
|
|
sklearn_quickstart.py
|
|
stable_diffusion.py
|
|
streaming_tutorial.py
|
|
test_service_pb2.py
|
|
test_service_pb2_grpc.py
|
|
transformers_example.py
|
|
translator_example.py
|
|
tutorial_batch.py
|
|
tutorial_pytorch.py
|
|
tutorial_sklearn.py
|
|
tutorial_tensorflow.py
|
|
varying_deps.py
|
|
vllm_example.py
|
|
whisper_example.py
|