Cloud GPU Resources and Pricing(fullstackdeeplearning.com)146 points by nihit-desai 3 years ago | 52 comments
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs(baseten.co)215 points by philipkiely 1 year ago | 142 comments
Finetuning LLMs on a Single GPU Using Gradient Accumulation(lightning.ai)76 points by ashvardanian 3 years ago | 2 comments
Show HN: ServerlessAI – Build, scale, and monetize AI apps without back end(serverlessai.dev)57 points by HeavenFox 2 years ago | 23 comments
WebGPU and the Price of Compiling WGSL(hugodaniel.com)38 points by todsacerdoti 1 year ago | 15 comments