Search papers, labs, and topics across Lattice.
Independent Researcher
2
0
5
Ditch static data paths: TENT dynamically slices and sprays LLM data across heterogeneous interconnects, self-healing in under 50ms and boosting throughput by up to 36%.
Training speculative decoding models just got an order of magnitude faster, unlocking real-world deployment with a new open-source framework and a suite of production-ready draft models.
