Parallax by Gradient
Host LLMs across devices sharing GPU to make your AI go brrr
835 followers
Host LLMs across devices sharing GPU to make your AI go brrr
835 followers
Your local AI just leveled up to multiplayer. Parallax is the easiest way to build your own AI cluster to run the best large language models across devices, no matter their specs or location.
Triforce Todos
How do you handle latency when devices are spread across different networks?
Parallax by Gradient
@abod_rehman Parallax uses PP instead of TP or EP to reduce the impact of latency between different network devices. We fully support PP and a series of other optimizations on GPUs and Macs to achieve better
Big fan of open models. Do you plan to open source the orchestration logic as well?
Parallax by Gradient
@azhar_muhammad Parallax is a fully open source framework, so here’s the orchestration logic in the code. If you have more interest in our strategy, you can go through the blog and paper about Parallax on our website
@joysong_j Looking forward to it!