chore: update parallelism docs (vipshop#346)

* chore: update parallelism docs

* chore: update parallelism docs

Author: DefTruth

README.md

@@ -6,7 +6,7 @@
     A <b>Unified</b>, Flexible and Training-free <b>Cache Acceleration</b> Framework for <b>🤗Diffusers</b> <br>
     ♥️ Cache Acceleration with <b>One-line</b> Code ~ ♥️ <br>
     🔥<a href="./docs/User_Guide.md">Forward Pattern Matching</a> | <a href="./docs/User_Guide.md">Automatic Block Adapter</a>🔥 <br>
-    🔥<a href="./docs/User_Guide.md"><b>DBCache</b></a> | <a href="./docs/User_Guide.md"><b>DBPrune</b></a> | <a href="./docs/User_Guide.md">Hybrid <b>TaylorSeer</b> Calibrator</a> | <a href="./docs/User_Guide.md">Hybrid <b>Cache CFG</b></a>🔥<br>
+    🔥<a href="./docs/User_Guide.md"><b>DBCache</b></a> | <a href="./docs/User_Guide.md"><b>DBPrune</b></a> | <a href="./docs/User_Guide.md">Hybrid <b>TaylorSeer</b> Calibrator</a> | <a href="./docs/User_Guide.md"><b>Cache CFG</b></a>🔥<br>
     🔥<a href="./docs/User_Guide.md"><b>Context Parallelism</b></a> | <a href="./docs/User_Guide.md"><b>Tensor Parallelism</b></a> | <a href="./docs/User_Guide.md">Low-bits Quantization</a>🔥<br>
     🔥<a href="./docs/User_Guide.md">Compile Compatible</a> | <a href="./docs/User_Guide.md"><b>🎉State-of-the-Art Performance</b></a>🎉 
   </p>

docs/User_Guide.md

@@ -538,7 +538,7 @@ cache_dit.enable_cache(
 
 <div id="context-parallelism"></div>
 
-cache-dit is compatible with context parallelism. Currently, we support the use of `Hybrid Cache` + `Context Parallelism` scheme (via NATIVE_DIFFUSER parallelism backend) in cache-dit. Users can use Context Parallelism to further accelerate the speed of inference! For more details, please refer to [📚examples/parallelism](https://github.com/vipshop/cache-dit/tree/main/examples/parallelism). Currently, cache-dit supported context parallelism for [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev), [Qwen-Image](https://github.com/QwenLM/Qwen-Image), [LTXVideo](https://huggingface.co/Lightricks/LTX-Video), [Wan2.1](https://github.com/Wan-Video/Wan2.1) and [Wan2.2](https://github.com/Wan-Video/Wan2.2). cache-dit will support more models in the future.
+cache-dit is compatible with context parallelism. Currently, we support the use of `Hybrid Cache` + `Context Parallelism` scheme (via NATIVE_DIFFUSER parallelism backend) in cache-dit. Users can use Context Parallelism to further accelerate the speed of inference! For more details, please refer to [📚examples/parallelism](https://github.com/vipshop/cache-dit/tree/main/examples/parallelism). Currently, cache-dit supported context parallelism for [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev), [Qwen-Image](https://github.com/QwenLM/Qwen-Image), [Qwen-Image-Lightning](https://github.com/ModelTC/Qwen-Image-Lightning), [LTXVideo](https://huggingface.co/Lightricks/LTX-Video), [Wan2.1](https://github.com/Wan-Video/Wan2.1) and [Wan2.2](https://github.com/Wan-Video/Wan2.2). cache-dit will support more models in the future.
 
 ```python
 # pip3 install "cache-dit[parallelism]"
@@ -557,7 +557,7 @@ cache_dit.enable_cache(
 
 <div id="tensor-parallelism"></div>
 
-cache-dit is also compatible with tensor parallelism. Currently, we support the use of `Hybrid Cache` + `Tensor Parallelism` scheme (via NATIVE_PYTORCH parallelism backend) in cache-dit. Users can use Tensor Parallelism to further accelerate the speed of inference and **reduce the VRAM usage per GPU**! For more details, please refer to [📚examples/parallelism](https://github.com/vipshop/cache-dit/tree/main/examples/parallelism). Currently, cache-dit supported tensor parallelism for [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev), [Qwen-Image](https://github.com/QwenLM/Qwen-Image), [Wan2.1](https://github.com/Wan-Video/Wan2.1) and [Wan2.2](https://github.com/Wan-Video/Wan2.2). cache-dit will support more models in the future.
+cache-dit is also compatible with tensor parallelism. Currently, we support the use of `Hybrid Cache` + `Tensor Parallelism` scheme (via NATIVE_PYTORCH parallelism backend) in cache-dit. Users can use Tensor Parallelism to further accelerate the speed of inference and **reduce the VRAM usage per GPU**! For more details, please refer to [📚examples/parallelism](https://github.com/vipshop/cache-dit/tree/main/examples/parallelism). Currently, cache-dit supported tensor parallelism for [FLUX.1](https://huggingface.co/black-forest-labs/FLUX.1-dev), [Qwen-Image](https://github.com/QwenLM/Qwen-Image), [Qwen-Image-Lightning](https://github.com/ModelTC/Qwen-Image-Lightning), [Wan2.1](https://github.com/Wan-Video/Wan2.1) and [Wan2.2](https://github.com/Wan-Video/Wan2.2). cache-dit will support more models in the future.
 
 ```python
 # pip3 install "cache-dit[parallelism]"