Update README.md

Author: lyogavin

README.md

@@ -1 +1,7 @@
+![airllm_logo](https://github.com/lyogavin/airllm/blob/main/assets/airllm_logo_sm.png?v=3&raw=true)
+
+**AirLLM** optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card without quantization, distillation and pruning. And you can run **405B Llama3.1** on **8GB vram** now.
+
+<a href="https://github.com/lyogavin/airllm/stargazers">![GitHub Repo stars](https://img.shields.io/github/stars/lyogavin/airllm?style=social)</a>
+
 Moved to here: https://github.com/lyogavin/airllm