diff --git a/README.md b/README.md
index 8c5f505..f0c2bae 100644
--- a/README.md
+++ b/README.md
@@ -22,6 +22,12 @@ interface, RESTful APIs compliant with OpenAI and Ollama, and even a simplified
 <br/><br/>
 Our vision for KTransformers is to serve as a flexible platform for experimenting with innovative LLM inference optimizations. Please let us know if you need any other features.
 
+<h2 id="Updates">🔥 Updates</h2>
+
+* **Aug 15, 2024**: Update detailed [TUTORIAL](doc/en/injection_tutorial.md) for injection and multi-GPU. 
+* **Aug 14, 2024**: Support llamfile as linear backend, 
+* **Aug 12, 2024**: Support multiple GPU; Support new model: mixtral 8\*7B  and 8\*22B; Support q2k, q3k, q5k dequant on gpu.
+* **Aug 9, 2024**: Support windows native.
 
 <h2 id="show-cases">🔥 Show Cases</h2>
 <h3>GPT-4-level Local VSCode Copilot on a Desktop with only 24GB VRAM</h3>
diff --git a/doc/en/injection_tutorial.md b/doc/en/injection_tutorial.md
index 655163e..5ebb327 100644
--- a/doc/en/injection_tutorial.md
+++ b/doc/en/injection_tutorial.md
@@ -165,7 +165,7 @@ Through these two rules, we place all previously unmatched layers (and their sub
 ## Muti-GPU
 
 If you have multiple GPUs, you can set the device for each module to different GPUs. 
-DeepseekV2-Chat got 60 layers, if we got 2 GPUs, we can allocate 30 layers to each GPU. Complete multi GPU rule examples [here](ktransformers/optimize/optimize_rules).
+DeepseekV2-Chat got 60 layers, if we got 2 GPUs, we can allocate 30 layers to each GPU. Complete multi GPU rule examples [here](https://github.com/kvcache-ai/ktransformers/blob/main/ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat-multi-gpu.yaml).
 
 
 <p align="center">