AdapTive-LeArning Speculator System (ATLAS): A New Paradigm in LLM Inference via Runtime-Learning Accelerators

Source evidence

What RADAR observed and classified to build this opportunity. It is what the source published, not a verification that the offer is still active.

• Together AI BlogObserved: Oct 10, 2025Source reliability: 60%

  AdapTive-LeArning Speculator System (ATLAS): A New Paradigm in LLM Inference via Runtime-Learning Accelerators. LLM inference that gets faster as you use it. Our runtime-learning accelerator adapts continuously to your workload, delivering 500 TPS on DeepSeek-V3.1, a 4x speedup over baseline performance without manual tuning.

  Open source