Add SGLang serving instructions

README.md

@@ -10,6 +10,8 @@ tags:
   - cosmos3
   - vllm
   - vllm-omni
+  - sglang
+  - sglang-diffusion
   - diffusers
   - text, image, video, audio, and action generation
   - omnimodel
@@ -922,6 +924,66 @@ Cosmos3 may produce imperfect outputs in challenging scenarios. Generation artif
 
 Cosmos3 outputs should not be treated as physically accurate simulation, reliable ground-truth reasoning, or safety-certified decision making. Applications involving robotics control, autonomous systems, scientific simulation, or safety-critical planning require additional validation, external constraints, system-level safety analysis, and domain-specific guardrails before deployment.
 
+
+## SGLang Serve
+
+[SGLang Diffusion](https://github.com/sgl-project/sglang) can serve Cosmos3-Nano through OpenAI-compatible image and video endpoints. Install SGLang from source with diffusion dependencies, then start a server:
+
+```shell
+git clone https://github.com/sgl-project/sglang.git
+cd sglang
+pip install -e "python[diffusion]"
+pip install "cosmos-guardrail==0.3.1"
+
+sglang serve --model-path nvidia/Cosmos3-Nano
+```
+
+For a video-specialized checkpoint, use `Cosmos3-Super-Image2Video` with multiple GPUs:
+
+```shell
+sglang serve \
+  --model-path nvidia/Cosmos3-Super-Image2Video \
+  --num-gpus 4
+```
+
+Supported SGLang endpoints:
+
+| Mode | Endpoint | Notes |
+| --- | --- | --- |
+| Text to image | `POST /v1/images/generations` | Returns base64 image data by default |
+| Text to video | `POST /v1/videos` | Creates an async job; poll `GET /v1/videos/{id}` and download `/content` |
+| Image to video | `POST /v1/videos` | Upload the conditioning image with `input_reference` |
+
+Example text-to-video request:
+
+```shell
+job_id=$(curl -sS -X POST http://localhost:30000/v1/videos \
+  --form-string "prompt=A small warehouse robot moves a blue box across a clean floor." \
+  --form-string "negative_prompt=blurry, distorted, low quality" \
+  --form-string "size=1280x720" \
+  --form-string "num_frames=81" \
+  --form-string "fps=24" \
+  --form-string "num_inference_steps=35" \
+  --form-string "guidance_scale=4.0" \
+  --form-string "flow_shift=10.0" \
+  --form-string "seed=42" \
+  --form-string 'extra_params={"guardrails":true,"use_resolution_template":false,"use_duration_template":false}' \
+  | python -c 'import json, sys; print(json.load(sys.stdin)["id"])')
+
+while true; do
+  status=$(curl -sS "http://localhost:30000/v1/videos/${job_id}" \
+    | python -c 'import json, sys; print(json.load(sys.stdin)["status"])')
+  [ "$status" = "completed" ] && break
+  [ "$status" = "failed" ] && exit 1
+  sleep 1
+done
+
+curl -sS -L "http://localhost:30000/v1/videos/${job_id}/content" \
+  -o cosmos3_t2v_output.mp4
+```
+
+SGLang accepts Cosmos 3 request options including `max_sequence_length`, `flow_shift`, `extra_params.guardrails`, `extra_params.use_resolution_template`, and `extra_params.use_duration_template`. Video-to-video, video-with-sound, and action generation are not supported by SGLang yet.
+
 ## Inference
 
 **Acceleration Engine:** [PyTorch](https://pytorch.org/), [vLLM](https://github.com/vllm-project/vllm), [vLLM-Omni](https://github.com/vllm-project/vllm-omni), [Hugging Face Diffusers](https://github.com/huggingface/diffusers)