Fix trtllm-serve command for TensorRT-LLM ToT Main

README.md

@@ -109,11 +109,13 @@ This model was obtained by quantizing the weights and activations of Wan2.2-T2V-
 
 ## Usage
 
-To serve this checkpoint with [TRTLLM](https://github.com/NVIDIA/TensorRT-LLM):
+To serve this checkpoint with [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/visual_gen/serve/README.md):
+
+Docker image used for the TensorRT-LLM example: `nvcr.io/nvidia/tensorrt-llm/release:1.4.0rc0`.
 
 ```sh
-# TRTLLM
-trtllm-serve nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4 --extra_visual_gen_options ./examples/visual_gen/serve/configs/wan.yml
+# TRTLLM (run from the root of the TensorRT-LLM source checkout)
+trtllm-serve nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4 --visual_gen_args ./examples/visual_gen/serve/configs/wan22.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.'