Search papers, labs, and topics across Lattice.
Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University
3
0
5
0
Achieving up to 16x faster attention computation with only a 1.76% accuracy loss could revolutionize the deployment of long-context LLMs in real-time applications.
FlexServe achieves over 10X faster secure LLM inference on mobile devices without compromising privacy or performance.
AI agents can now checkpoint and rollback sandbox states in milliseconds, unlocking deeper search and larger-scale fan-outs previously bottlenecked by slow state duplication.
