A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 05:15 UTC
[Docs] add Dynamo/aibrix integration and kubeai/aks link (#32767)
Signed-off-by: Paco Xu <paco.xu@daocloud.io>
Paco Xu committed
Mar 5, 2026 at 17:39 UTC
7493c51c5532c25e2f2573eb274461e39f7e2a0b
5 files changed
+16
-1
docs/deployment/integrations/aibrix.md
new
+5
@@ -0,0 +1,5 @@
1
+# AIBrix
2
+
3
+[AIBrix](https://github.com/vllm-project/aibrix) is a cloud-native control plane that integrates with vLLM to simplify Kubernetes deployment, scaling, routing, and LoRA adapter management for large language model inference.
4
+
5
+For installation and usage instructions, please refer to the [AIBrix documentation](https://aibrix.readthedocs.io/).
docs/deployment/integrations/dynamo.md
new
+7
@@ -0,0 +1,7 @@
1
+# NVIDIA Dynamo
2
+
3
+[NVIDIA Dynamo](https://github.com/ai-dynamo/dynamo) is an open-source framework for distributed LLM inference that can run vLLM on Kubernetes with flexible serving architectures (e.g. aggregated/disaggregated, optional router/planner).
4
+
5
+For Kubernetes deployment instructions and examples (including vLLM), see the [Deploying Dynamo on Kubernetes](https://github.com/ai-dynamo/dynamo/blob/main/docs/kubernetes/README.md) guide.
6
+
7
+Background reading: InfoQ news coverage — [NVIDIA Dynamo simplifies Kubernetes deployment for LLM inference](https://www.infoq.com/news/2025/12/nvidia-dynamo-kubernetes/).
docs/deployment/integrations/kubeai.md
+1
@@ -5,6 +5,7 @@
5
Please see the Installation Guides for environment specific instructions:
6
7
- [Any Kubernetes Cluster](https://www.kubeai.org/installation/any/)
8
+- [AKS](https://www.kubeai.org/installation/aks/)
9
- [EKS](https://www.kubeai.org/installation/eks/)
10
- [GKE](https://www.kubeai.org/installation/gke/)
11
docs/deployment/k8s.md
+2
-1
@@ -11,6 +11,7 @@ Deploying vLLM on Kubernetes is a scalable and efficient way to serve machine le
11
Alternatively, you can deploy vLLM to Kubernetes using any of the following:
12
13
- [Helm](frameworks/helm.md)
14
+- [NVIDIA Dynamo](integrations/dynamo.md)
15
- [InftyAI/llmaz](integrations/llmaz.md)
16
- [llm-d](integrations/llm-d.md)
17
- [KAITO](integrations/kaito.md)
@@ -20,7 +21,7 @@ Alternatively, you can deploy vLLM to Kubernetes using any of the following:
21
- [kubernetes-sigs/lws](frameworks/lws.md)
22
- [meta-llama/llama-stack](integrations/llamastack.md)
23
- [substratusai/kubeai](integrations/kubeai.md)
23
-- [vllm-project/aibrix](https://github.com/vllm-project/aibrix)
24
+- [vllm-project/AIBrix](integrations/aibrix.md)
25
- [vllm-project/production-stack](integrations/production-stack.md)
26
27
## Deployment with CPUs
pyproject.toml
+1
@@ -177,6 +177,7 @@ Pn = "Pn"
177
arange = "arange"
178
PARD = "PARD"
179
pard = "pard"
180
+AKS = "AKS"
181
182
[tool.typos.type.py]
183
extend-glob = []