Everything tagged AI inference.
OpenAI unveiled Ultrafast on August 13, a preview tier it says runs GPT-5.6 Sol up to 14 times faster on Cerebras' wafer-scale hardware.
AMD agreed to acquire Taalas, a Toronto startup that etches AI model weights directly into silicon to cut inference costs, on August 6, 2026.
AMD and Cerebras unveiled a disaggregated AI inference partnership claiming up to five times higher tokens per second per watt, launching first on…
