Fix outdated SGLang diffusion documentation links (#314)

Author: JiaxinD

blog/2025-11-07-sglang-diffusion.md

@@ -7,7 +7,7 @@ previewImg: /images/blog/sgl-diffusion/sgl-diffusion-banner-16-9.png
 
 We are excited to introduce SGLang Diffusion, which brings SGLang's state-of-the-art performance to accelerate image and video generation for diffusion models.
 SGLang Diffusion supports major open-source video and image generation models (Wan, Hunyuan, Qwen-Image, Qwen-Image-Edit, Flux) while providing fast inference speeds and ease of use via multiple API entry points (OpenAI-compatible API, CLI, Python interface). SGLang Diffusion delivers 1.2x - 5.9x speedup across diverse workloads.
-In collaboration with the FastVideo team, we provide a complete ecosystem for diffusion models, from post-training to production serving. The code is available [here](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen).
+In collaboration with the FastVideo team, we provide a complete ecosystem for diffusion models, from post-training to production serving. The code is available [here](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen). Documentation is available [here](https://docs.sglang.io/diffusion/index.html).
 
 <iframe
 width="600"
@@ -56,7 +56,7 @@ We support various popular open-source video & image generation models, includin
   - Video models: Wan-series, FastWan, Hunyuan
   - Image models: Qwen-Image, Qwen-Image-Edit, Flux
 
-For full list of supported models, reference [here](https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/docs/support_matrix.md).
+For full list of supported models, reference [here](https://docs.sglang.io/diffusion/compatibility_matrix.html).
 
 ## Usage
 
@@ -101,7 +101,7 @@ sglang generate --model-path black-forest-labs/FLUX.1-dev \
   --save-output
 ```
 
-Reference [install guide](https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/docs/install.md) and [cli guide](https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/docs/cli.md) for more installation methods.
+Reference [install guide](https://docs.sglang.io/diffusion/installation.html) and [cli guide](https://docs.sglang.io/diffusion/api/cli.html) for more installation methods.
 
 ### Demo
 

blog/2026-01-16-sglang-diffusion.md

@@ -152,7 +152,7 @@ Furthermore, we can now integrate and refine Cache-DiT optimizations to our newl
 ### 4. Few More Things
 
 - **Memory Monitoring**: Peak usage statistics available across offline generation and online serving workflows.
-- [**Profiling Suite**](https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/docs/profiling.md):
+- [**Profiling Suite**](https://docs.sglang.io/diffusion/performance/profiling.html):
   Full-stage support with step-by-step docs for PyTorch Profiler and Nsight Systems.
 - [**Diffusion Cookbook**](https://cookbook.sglang.io/docs/diffusion/): Curated recipes, best practices, and
   benchmarking guides for SGLang-Diffusion.
@@ -183,5 +183,5 @@ Special thanks to AMD for their compute support and assistance in development.
 
 - **Slack channel**: [#diffusion](https://sgl-fru7574.slack.com/archives/C09P0HTKE6A) (join via slack.sglang.io)
 - [**Cookbook for SGLang-Diffusion**](https://cookbook.sglang.io/docs/diffusion)
-- [**Documentation on SGLang-Diffusion**](https://github.com/sgl-project/sglang/blob/main/python/sglang/multimodal_gen/docs)
+- [**Documentation on SGLang-Diffusion**](https://docs.sglang.io/diffusion/index.html)
 - [**Roadmap for 26Q1**](https://github.com/sgl-project/sglang/issues/18286)