#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
RsS iS dEaD LOL: discover RSS Feeds of your follows on Mastodon
频道曾经提及过一个叫 FeedsMage 的服务,用于从你 fo 的推友的 Bio 里找链接,再从链接里找 Feed ,最后可生成一个 #OPML 文件。RsS iS dEaD LOL 则是长毛象版的 FeedsMage,从你 fo 的 Fediverse 用户的 Bio 里找链接,发现 RSS,然后可生成 #OPML:
https://rss-is-dead.lol/
例如我的:
https://rss-is-dead.lol/user?profileUrl=https%3A%2F%2Fmastodon.social%2Fusers%2FAboutRSS
发现于作者嘟文:
https://mastodon.social/@paulcuth/112178886374464145