Show HN: Llm.f90 fast, hackable transformer implementation in Fortran I submitted an earlier version of this a few months ago (as llama2.f90). At that time it had a lot of steps to run and was just a toy, now it's easy to run and is a competitive option for llm inference. See the motivation section for discussion and the `Performance` issue for an ongoing discussion about performance. https://ift.tt/5U978Jh November 14, 2023 at 01:17AM
Show HN: Llm.f90 fast, hackable transformer implementation in Fortran https://ift.tt/AR9eCrL
Related Articles
Show HN: A guide to self-host AudioCraft demo https://ift.tt/Ba9Yfj0Show HN: A guide to self-host AudioCraft demo https://ift.tt/hKXs8G2 A… Read More
Show HN: ChatData-yet another chat-with-document app, querying millions of files https://ift.tt/j2qtJhzShow HN: ChatData-yet another chat-with-document app, querying million… Read More
Show HN: Create books on any topic with ChatGPT https://ift.tt/pz5Da6CShow HN: Create books on any topic with ChatGPT This weekend wanted to… Read More
Show HN: I created an app to transfer files from my PC to any device wirelessly https://ift.tt/P1U2cz9Show HN: I created an app to transfer files from my PC to any device w… Read More
Show HN: Tarot Arcana—AI tarot card readings https://ift.tt/nKfB4tFShow HN: Tarot Arcana—AI tarot card readings On device LLM generated t… Read More
Show HN: SillyCoValley – I made a fast-paced startup simulation game https://ift.tt/QCk6GajShow HN: SillyCoValley – I made a fast-paced startup simulation game h… Read More
Show HN: Carbonyl Terminal – A Windows/Linux/macOS Client for Carbonyl Browser https://ift.tt/9bDIfcWShow HN: Carbonyl Terminal – A Windows/Linux/macOS Client for Carbonyl… Read More
Show HN: Archsense – Accurately generated architecture from the source code https://ift.tt/iaUQe7AShow HN: Archsense – Accurately generated architecture from the source… Read More
0 Comments: