add news (#192)

* add news

* minor

* minor

* fix typo

---------

Co-authored-by: Holden <hodlenx@gmail.com>

README.md

@@ -8,6 +8,8 @@ PowerInfer is a CPU/GPU LLM inference engine leveraging **activation locality**
 [Project Kanban](https://github.com/orgs/SJTU-IPADS/projects/2/views/2)
 
 ## Latest News 🔥
+- [2024/6/11] We are thrilled to introduce [PowerInfer-2](https://arxiv.org/abs/2406.06282), our highly optimized inference framework designed specifically for smartphones. With TurboSparse-Mixtral-47B, it achieves an impressive speed of 11.68 tokens per second, which is up to 23 times faster than other state-of-the-art frameworks.
+- [2024/6/11] We are thrilled to present [Turbo Sparse](https://arxiv.org/abs/2406.05955), our TurboSparse models for fast inference. With just $0.1M, we sparsified the original Mistral and Mixtral model to nearly 90% sparsity while maintaining superior performance! For a Mixtral-level model, our TurboSparse-Mixtral activates only **4B** parameters!
 - [2024/5/20] **Competition Recruitment: CCF-TCArch Customized Computing Challenge 2024**. The CCF TCARCH CCC is a national competition organized by the Technical Committee on Computer Architecture (TCARCH) of the China Computer Federation (CCF). This year's competition aims to optimize the PowerInfer inference engine using the open-source ROCm/HIP. More information about the competition can be found [here](https://ccf-tcarch-ccc.github.io/2024/).
 - [2024/5/17] We now provide support for AMD devices with ROCm. (WIP - there are known issues for models exceeding 40B).
 - [2024/3/28] We are trilled to present [Bamboo LLM](https://github.com/SJTU-IPADS/Bamboo) that achieves both top-level performance and unparalleled speed with PowerInfer! Experience it with Bamboo-7B [Base](https://huggingface.co/PowerInfer/Bamboo-base-v0.1-gguf) / [DPO](https://huggingface.co/PowerInfer/Bamboo-DPO-v0.1-gguf).