mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
1fc8bd3cd8
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
9 lines
415 B
ReStructuredText
9 lines
415 B
ReStructuredText
Dynamo K8s Example
|
|
=================================
|
|
|
|
This example demonstrates how to deploy TensorRT-LLM on a Kubernetes cluster
|
|
using Dynamo Cloud. Dynamo provides an operator-based approach to manage the
|
|
lifecycle of model deployments through Custom Resource Definitions (CRDs).
|
|
Please see `Dynamo Kubernetes Quick Start Guide <https://docs.nvidia.com/dynamo/latest/kubernetes/README.html>`_
|
|
for more details.
|