Speeding up your LLM inference with PARD (Parallel Draft Models), achieving up to 3.3x perf boost on llama 3 family of models!!!

www.amd.com/en/developer...

AITER is all you need!!!

AI Tensor Engine for ROCm (AITER) a centralized repository for AMD high performance kernels that drastically boost inference and training performance.

rocm.blogs.amd.com/software-too...

Introducing Instella-VL-1B, AMD first vision language model!!! Trained on MI300X and fully open. Kudo to AMD GenAI Research team. #AMD #AI #ML #LLM #Vision #ROCm #AMDGPU

rocm.blogs.amd.com/artificial-i...

Learn how to get the best performance out of MI300X, and take advantage of its memory capacity and bandwidth!!! #AMD #AI #ML #AGI #DeepLearning #HW #GPU

rocm.blogs.amd.com/artificial-i...