Hackers repurpose a PS5 to run local AI, with surprising results
PS5LM Plus, an open-source project, uses the PlayStation 5's GPU to run AI models locally at more than 100 tokens per second. It only works on modified consoles.
Related stories
A new French AI is coming at the end of November: after Mistral, OVHcloud joins the race
OVHcloud's boss revealed that the French cloud provider is developing its own large language model. A first version could launch at the end of November.
IBM-backed llm-d framework adds controls for running AI models in-house
IBM and other contributors released version 1.0 of llm-d, an open-source distributed inference framework, ahead of PyTorch Conference North America. The release adds operational controls to help enterprises run large models reliably on their own infrastructure.
DeepSeek open-sources DeepInfer, the inference framework behind DeepSeek-V4.1-Flash
DeepSeek released DeepInfer under Apache 2.0, the framework it uses to serve DeepSeek-V4.1-Flash in production. It targets NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs and currently supports offline inference only.
Latest open artifacts (#25): DeepSeek V4.1 Flash 1017, American-made models, and new regulatory controls in the US and China
Interconnects' regular roundup of open models covers DeepSeek V4.1 Flash 1017, new American-made models and fresh regulatory controls in the US and China. The author frames it as Western open models striking back.
Hugging Face ❤️ TorchTPU: TPUs, natively
Hugging Face published a post about TorchTPU, presented as a way to use TPUs natively. The headline signals support for the backend in the Hugging Face ecosystem.