AIR#264 - Llama 3.1 Breaks Speed Records & Discover Black Holes with Your iPhone!
Hey there! Here's the latest AI news for today. Enjoy! Today's top stories 🔥 Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference Llama 3.1 405B achieves record speed of 969 tokens/s on Cerebras Inference, outperforming competitors in latency and context