Skip to content

SGLang

This example shows how to deploy DeepSeek-R1-Distill-Llama 8B and 70B using SGLang and dstack.

Apply a configuration

Here's an example of a service that deploys DeepSeek-R1-Distill-Llama 8B and 70B using SgLang.

type: service
name: deepseek-r1-nvidia

image: lmsysorg/sglang:latest
env:
  - MODEL_ID=deepseek-ai/DeepSeek-R1-Distill-Llama-8B

commands:
  - python3 -m sglang.launch_server
     --model-path $MODEL_ID
     --port 8000
     --trust-remote-code

port: 8000
model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B

resources:
   gpu: 24GB


type: service
name: deepseek-r1-amd

image: lmsysorg/sglang:v0.4.1.post4-rocm620
env:
  - MODEL_ID=deepseek-ai/DeepSeek-R1-Distill-Llama-70B

commands:
  - python3 -m sglang.launch_server
     --model-path $MODEL_ID
     --port 8000
     --trust-remote-code

port: 8000
model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B

resources:
  gpu: MI300x
  disk: 300GB

To run a configuration, use the dstack apply command.

$ dstack apply -f examples/llms/deepseek/sglang/amd/.dstack.yml

 #  BACKEND  REGION     RESOURCES                         SPOT  PRICE
 1  runpod   EU-RO-1   24xCPU, 283GB, 1xMI300X (192GB)    no    $2.49

Submit the run deepseek-r1-amd? [y/n]: y

Provisioning...
---> 100%

Once the service is up, the model will be available via the OpenAI-compatible endpoint at <dstack server URL>/proxy/models/<project name>/.

curl http://127.0.0.1:3000/proxy/models/main/chat/completions \
    -X POST \
    -H 'Authorization: Bearer &lt;dstack token&gt;' \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
      "messages": [
        {
          "role": "system",
          "content": "You are a helpful assistant."
        },
        {
          "role": "user",
          "content": "What is Deep Learning?"
        }
      ],
      "stream": true,
      "max_tokens": 512
    }'

SGLang Model Gateway

If you'd like to use a custom routing policy, e.g. by leveraging the SGLang Model Gateway, create a gateway with router set to sglang. Check out gateways for more details.

If a gateway is configured (e.g. to enable auto-scaling or HTTPs, rate-limits, etc), the OpenAI-compatible endpoint is available at https://gateway.<gateway domain>/.

Source code

The source-code of this example can be found in examples/llms/deepseek/sglang.

What's next?

  1. Read about services and gateways
  2. Browse the SgLang DeepSeek Usage, Supercharge DeepSeek-R1 Inference on AMD Instinct MI300X