Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
3
3
Train LLMs with up to $1.455\times$ less memory and enable $3.5\times$ longer context lengths by losslessly compressing tensors on-the-fly.
Lossless compression of sparse ReLU activations slashes LLM activation VRAM by up to 31% with near-zero overhead.