Popular repositories Loading

1. airllm airllm Public

   🚀 Optimize memory for large language models, enabling 70B models on a 4GB GPU and 405B Llama3.1 on 8GB VRAM without compression techniques.

2. yhinsson.github.io yhinsson.github.io Public

   🚀 Optimize inference memory to run 70B language models on a 4GB GPU, and process 405B Llama3.1 with just 8GB VRAM.