#cplusplus
FlashMLA is DeepSeek's optimized attention library that makes AI models run faster and use less memory. It works with advanced NVIDIA GPUs to speed up how language models process information, achieving up to 660 trillion floating-point operations per second. The library supports both dense and sparse attention modes, meaning it can focus on important tokens while skipping less relevant ones, reducing computational waste. For you, this means faster AI responses, lower costs for running large language models, and better performance on tasks like chatbots and code generation. The technology is open-source and integrates with popular AI frameworks like PyTorch and Hugging Face, making it accessible for developers building next-generation AI applications.
https://github.com/deepseek-ai/FlashMLA
LDS PREPAREDNESS MANUAL
From Chat
It's from LDS, which is whatever, but its one of the most comprehensive pepper manuals I've ever seen
#Prepping#Prepper
https://permacomputing.net/
数字领域的朴门实践正在芬兰萌芽!
New to permacomputing?
Permacomputing is a more sustainable approach to computer and network technology inspired by permaculture. Permacomputing is both a concept and a community of practice oriented around issues of resilience and regenerativity in digital technology.
In a time where computing epitomizes industrial waste, permacomputing encourages a more sustainable approach, maximizing hardware lifespans, minimizing energy use and focussing on the use of already available computational resources. We do this because humans are part of nature and technology is an extension of humans, and we acknowledge that technology has been used to harm nature. We want to find out how we can practice good relations with the Earth by learning from ecological systems to leverage and re-center existing technologies and practices. We are also interested in investigating what a permacomputing way of life could be, and what sort of transformative computational culture and aesthetics it could bring forward.
If you want to know more, please start reading about what is permacomputing in essence, and then dive into its principles.
Wiki
Started in May 2022, the permacomputing wiki is where we maintain a set of principles, collectively document practical perspectives and interpretations of these principles, and offer more speculative reflections on permacomputing.
The wiki is still at a very early stage of development, we are frequently working on it.
This main page of the wiki is an index to the various topics covered. See "about" for a more detailed discussion about the wiki itself.
#致呼吸不畅的数字生活#DIY#prepper