Search papers, labs, and topics across Lattice.
4
0
7
Despite executing target instructions, LLMs often fail to deliver competitive performance in GPU kernel optimization, especially on complex tasks.
Scaling prompt learning by 17x without sacrificing accuracy is now possible, unlocking efficient self-improvement for LLM agents.
Forget scaling compute – the future of AI hinges on a 1000x leap in energy efficiency via tight AI+Hardware co-design over the next decade.
Open-source LLMs can now autonomously optimize AI accelerator kernels, matching the performance of proprietary models at a fraction of the cost.
