Update README.md

README.md

@@ -61,7 +61,7 @@ Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated sys
 
 ## Software Integration:
 **Supported Runtime Engine(s):** <br>
-* TRTLLM <br>
+* TRTLLM,SGLang <br>
 
 **Supported Hardware Microarchitecture Compatibility:** <br>
 * NVIDIA Blackwell <br>
@@ -101,7 +101,7 @@ The model is quantized with nvidia-modelopt **v0.42.0**  <br>
 
 
 ## Inference:
-**Acceleration Engine:** TRTLLM <br>
+**Acceleration Engine:** TRTLLM,SGLang <br>
 **Test Hardware:** B200 <br>
 
 ## Post Training Quantization
@@ -112,7 +112,34 @@ This model was obtained by quantizing the weights and activations of Wan2.2-T2V-
 To serve this checkpoint with [TRTLLM](https://github.com/NVIDIA/TensorRT-LLM):
 
 ```sh
+# TRTLLM
 trtllm-serve nvidia/Wan2.2-T2V-A14B-Diffusers-FP8 --extra_visual_gen_options ./examples/visual_gen/serve/configs/wan.yml
+
+# SGLang
+
+PROMPT='A cat and a dog baking a cake together in a cozy kitchen. The cat carefully measures flour while the dog stirs batter in a glass bowl, sunlight through the window, smooth cinematic camera motion.'
+
+FLASHINFER_DISABLE_VERSION_CHECK=1 
+python -m sglang.multimodal_gen.runtime.entrypoints.cli.main generate 
+--model-path nvidia/Wan2.2-T2V-A14B-Diffusers-FP8 
+--backend sglang 
+--attention-backend torch_sdpa 
+--performance-mode speed 
+--dit-cpu-offload false 
+--dit-layerwise-offload false 
+--text-encoder-cpu-offload false 
+--image-encoder-cpu-offload false 
+--vae-cpu-offload false 
+--pin-cpu-memory false 
+--width 832 
+--height 480 
+--num-frames 81 
+--fps 16 
+--num-inference-steps 50 
+--guidance-scale 5.0 
+--seed 0 
+--warmup false 
+--prompt "$PROMPT" 
 ```
 
 ### Model Characteristics