Update README.md

README.md

@@ -74,9 +74,9 @@ What is truly exciting is that in the comparison with Qwen3-32B, Ring-flash-line
 
 <div align="center">
 
-|     **Model**      | **#Total Params** | **#Activated Params** | **Context Length** | **Download** |
-| :----------------: | :---------------: | :-------------------: | :----------------: | :----------: |
-| Ring-flash-linear-2.0 |       100B       |         6.1B         |        128K         |      [🤗 HuggingFace](https://huggingface.co/inclusionAI/Ring-flash-linear-2.0) <br>[🤖 Modelscope](https://modelscope.cn/models/inclusionAI/Ring-flash-linear-2.0)|
+|     **Model**      | **Context Length** | **Download** |
+| :----------------: | :----------------: | :----------: |
+| Ring-flash-linear-2.0 |        128K         |      [🤗 HuggingFace](https://huggingface.co/inclusionAI/Ring-flash-linear-2.0) <br>[🤖 Modelscope](https://modelscope.cn/models/inclusionAI/Ring-flash-linear-2.0)|
 </div>
 
 ## Quickstart
@@ -86,8 +86,6 @@ What is truly exciting is that in the comparison with Qwen3-32B, Ring-flash-line
 ```bash
 pip install flash-linear-attention==0.3.2
 pip install transformers==4.56.1
-pip install sgl-kernel==0.3.9.post2
-pip install vllm==0.10.2
 ```
 
 ### 🤗 Hugging Face Transformers