Optimizing a Rust GPU matmul kernel(rust-gpu.github.io)82 points by lukastyrychtr 1 year ago | 7 comments
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs(baseten.co)215 points by philipkiely 1 year ago | 142 comments
Tinygrad and rusticl and aco: why not?(airlied.blogspot.com)39 points by pantalaimon 3 years ago | 28 comments
What happens when a GPU writes memory(blog.doubleword.ai)61 points by ibobev 1 month ago | 1 comments