Fly Kubernetes(fly.io)
223 points by ferriswil | 138 comments
223 points by ferriswil | 138 comments
167 points by darthShadow | 27 comments
456 points by Lwrless | 128 comments
Fly.io blog post describing how they provision WireGuard peers just-in-time across their gateway infrastructure.
185 points by rrampage | 130 comments
235 points by mkeeter | 149 comments
344 points by kiwicopple | 130 comments
Fly.io blog post introducing FLAME, an approach to serverless-style elastic scaling that runs app code on short-lived machines, built around Elixir.
834 points by mxstbr | 529 comments
Fly.io blog post reflecting on how the company's bet on offering GPU machines to developers did not pan out as expected.
1056 points by nmstoker | 243 comments
Stanford Hazy Research blog post on what GPU hardware wants for efficient AI kernels, introducing the ThunderKittens CUDA kernel library.
441 points by meetpateltech | 569 comments
OpenAI announcement of a strategic partnership with NVIDIA to deploy 10 gigawatts of NVIDIA systems for its AI infrastructure.
578 points by tosh | 194 comments
Ollama blog post from March 14, 2024 announcing preview support for running models on AMD graphics cards.
571 points by emrah | 259 comments
Google Developers Blog post announcing Gemma 3 models trained with quantization-aware training so they can run on consumer GPUs.
399 points by DvdGiessen | 408 comments
Blog post by Matthew Garrett arguing that GPUs, not TPMs, are the real root of hardware DRM; the capture shows a Dreamwidth captcha page instead.