Search papers, labs, and topics across Lattice.
University of California Santa Cruz
3
0
5
Concordia achieves fault tolerance for LLM inference by seamlessly integrating persistent kernel checkpointing, enabling rapid recovery without CPU bottlenecks.
FlowPaint enables censorship evasion through a single prompt, transforming complex evasion techniques into an intuitive semantic editing task.
Kernel launch overhead is a bigger bottleneck than you think: GPUOS achieves up to 15.3x speedup by fusing operations at runtime.
