# Deploying a RoCE Network-Based SGLANG Two-Node Inference Service on a Kubernetes (K8S) Cluster
LeaderWorkerSet (LWS) is a Kubernetes API that aims to address common deployment patterns of AI/ML inference workloads. A major use case is for multi-host/multi-node distributed inference.
Sglang can also be deployed with LWS on Kubernetes for distributed model serving.
Please see this guide for more details on deploying SGLang on Kubernetes using LWS.
Here we take the deployment of deepseekR1 as an example.
## Prerequisites
1. At least two Kubernetes nodes, each with 2 H20 systems and 8 GPUs, are required.
2. Make sure your K8S cluster has LWS correctly installed. If it hasn't been set up yet, please follow the instructions in this [document](https://github.com/kubernetes-sigs/lws/blob/main/docs/setup/install.md)
## Basic Example
The Basic Example documentation is introduced here: [visit this guide](https://github.com/kubernetes-sigs/lws/tree/main/docs/examples/sglang)
However, that document only covers the basic NCCL socket mode.
In this section, we’ll make some simple modifications to adapt the setup to the RDMA scenario.
[2025-02-17 05:27:32] INFO: 127.0.0.1:48924 - "POST /generate HTTP/1.1" 200 OK
[2025-02-17 05:27:32] The server is fired up and ready to roll!
```
if not successfully startup, please follow this steps to check or see the remaining issues... thanks.
### Debug
* Set `NCCL_DEBUG=TRACE` to check if it is a nccl communication problem
This should resolve most NCCL-related issues.
***Noticed: If you find that NCCL_DEBUG=TRACE is not effective in the container environment, but the process is stuck or you encounter hard-to-diagnose issues, try switching to a different container image. Some images may not handle standard error output properly.***
#### ROCE scenario
* Please make sure that RDMA devices are available in the cluster environment.
* Please make sure that the nodes in the cluster have mellanox NICs with RoCE. In this example, we use mellanox ConnectX 5 model NICs, and the proper OFED driver has been installed, if not, please refer to the document Install OFED Driver to install the driver.
8/1: mlx5_bond_0/1: state ACTIVE physical_state LINK_UP netdev reth0
9/1: mlx5_bond_1/1: state ACTIVE physical_state LINK_UP netdev reth2
10/1: mlx5_bond_2/1: state ACTIVE physical_state LINK_UP netdev reth4
11/1: mlx5_bond_3/1: state ACTIVE physical_state LINK_UP netdev reth6
$ ibdev2netdev
8/1: mlx5_bond_0/1: state ACTIVE physical_state LINK_UP netdev reth0
9/1: mlx5_bond_1/1: state ACTIVE physical_state LINK_UP netdev reth2
10/1: mlx5_bond_2/1: state ACTIVE physical_state LINK_UP netdev reth4
11/1: mlx5_bond_3/1: state ACTIVE physical_state LINK_UP netdev reth6
```
* test roce network speed in th host
```shell
yum install qperf
# for server：
excute qperf
# for client
qperf -t 60 -cm1 <server_ip> rc_rdma_write_bw
```
* check rdma accessible in your container...
```shell
# ibv_devices
# ibv_devinfo
```
## Keys to Success
* In the YAML configuration above, pay attention to the NCCL environment variable. For older versions of NCCL, you should check the NCCL_IB_GID_INDEX environment setting.
* NCCL_SOCKET_IFNAME is also crucial, but in a containerized environment, this typically isn’t an issue.
* In some cases, it’s necessary to configure GLOO_SOCKET_IFNAME correctly.
* NCCL_DEBUG is essential for troubleshooting, but I've found that sometimes it doesn't show error logs within containers. This could be related to the Docker image you're using. You may want to try switching images if needed.
* Avoid using Docker images based on Ubuntu 18.04, as they tend to have compatibility issues.
## Remaining issues
* In Kubernetes, Docker, or Containerd environments, we use hostNetwork to prevent performance degradation.
* We utilize privileged mode, which isn’t secure. Additionally, in containerized environments, GPU isolation cannot be fully achieved.
## Todo
* Integrated with [k8s rdma share plugin](https://github.com/Mellanox/k8s-rdma-shared-dev-plugin).
