Add SGLang serving instructions

README.md

@@ -9,6 +9,8 @@ tags:
   - cosmos
   - cosmos3
   - vllm-omni
+  - sglang
+  - sglang-diffusion
   - diffusers
   - image-to-video
   - video-generation
@@ -412,6 +414,50 @@ python scripts/upsample_prompt.py \
     --output-path scripts/upsampled.json
 ```
 
+### SGLang
+
+SGLang-Diffusion can serve `nvidia/Cosmos3-Super-Image2Video` through the OpenAI-compatible async video endpoint. Install SGLang from source with diffusion dependencies, then start the server:
+
+```bash
+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-Super-Image2Video \
+  --num-gpus 4
+```
+
+Example image-to-video request:
+
+```bash
+job_id=$(curl -sS -X POST http://localhost:30000/v1/videos \
+  --form-string "prompt=A small warehouse robot moves a blue box across a clean floor." \
+  --form-string "negative_prompt=blurry, distorted, low quality" \
+  --form-string "size=1280x720" \
+  --form-string "num_frames=81" \
+  --form-string "fps=24" \
+  --form-string "num_inference_steps=35" \
+  --form-string "guidance_scale=4.0" \
+  --form-string "flow_shift=10.0" \
+  --form-string "seed=42" \
+  --form-string 'extra_params={"guardrails":true,"use_resolution_template":false,"use_duration_template":false}' \
+  -F "input_reference=@input.png" \
+  | python -c 'import json, sys; print(json.load(sys.stdin)["id"])')
+
+while true; do
+  status=$(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_super_i2v_output.mp4
+```
+
 ### Diffusers
 
 Cosmos3 is fully supported within the popular HuggingFace Diffusers package. This integration makes it a supported inference backend, allowing developers to easily incorporate Cosmos3's capabilities - such as text-to-image generation - into their pipelines using the Cosmos3OmniPipeline class, as demonstrated by the provided code examples (see examples for other modalities on the HuggingFace Cosmos3 page).