Update docs/contributing/features/cfg_parallel.md

Co-authored-by: Canlin Guo <961750412@qq.com>
Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>

Author: wtomin

docs/contributing/features/cfg_parallel.md

@@ -17,7 +17,7 @@ In standard Classifier-Free Guidance, each diffusion step requires two forward p
 
 ### Architecture
 
-vLLM-omni provides `CFGParallelMixin` that encapsulates all CFG parallel logic. Pipelines inherit from this mixin and implement a `diffuse()` method that orchestrates the denoising loop.
+vLLM-Omni provides `CFGParallelMixin` that encapsulates all CFG parallel logic. Pipelines inherit from this mixin and implement a `diffuse()` method that orchestrates the denoising loop.
 
 
 | Method | Purpose | Automatic Behavior |