News for hackers. Stuff that matters.
Re:Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs by diggan on Thursday August 07, 2025 @05:34AM (#44822445)
In the case of the GPT-OSS models, the worst (time consuming) part of supporting it is the new format they've trained the model with, "OpenAI harmony", in my own clients I couldn't just replace the model and call it a day, but still working on getting then to work correctly with tool calling...

There are no comments on this comment yet.