Models & Labs
OpenAI previews Ultrafast mode for GPT-5.6 Sol
OpenAIhigh confidence
Why it matters
- →Ultrafast mode significantly reduces AI processing time, enhancing real-time application potential.
- →The use of Cerebras technology showcases innovative hardware integration in AI.
- →Faster token output can improve user experience and efficiency in AI-driven tasks.
OpenAI has announced a preview of its new Ultrafast API service tier, which accelerates the performance of GPT-5.6 Sol by up to 14 times. This speed increase is achieved through the use of Cerebras technology, enabling the model to produce up to 750 output tokens per second. The Ultrafast mode aims to enhance the efficiency of AI applications, potentially benefiting developers and businesses by reducing latency in AI interactions. This preview marks a significant advancement in AI processing capabilities.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
