Y Hacker News new | ask | show | jobs

user: junrushao1994 created: 2018-07-12 karma: 336 Junru Shao junrushao1994 at gmail.com Options are my own submissions: 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments Scaling LLama2-70B with Multiple Nvidia/AMD GPU 13 points | 6 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments MLC LLM: 70B Llama-2-4bit on MacBook at 50%-80% speed of A100 12 points | 3 comments Running RedPajama and other open LLMs on phones, browsers and AMD/NV/Intel GPUs 11 points | 0 comments MLC: Bringing Hardware Accelerated Language Models to Consumer Devices 8 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments