Run 70B LLM Inference on a Single 4GB GPU with This New Technique(ai.gopubby.com)80 points by gardenfelder 2 years ago | 39 comments
Compiling LLMs into a MegaKernel: A path to low-latency inference(zhihaojia.medium.com)291 points by matt_d 1 year ago | 74 comments
Learnings from our years of Kubernetes in production(medium.com)193 points by jonsson101 2 years ago | 169 comments
What I think about Lua after shipping a project with 60k lines of code(blog.luden.io)294 points by gamescodedogs 2 years ago | 222 comments