Search papers, labs, and topics across Lattice.
4
0
6
5
FIBER achieves up to 2.25x speedup in LLM serving by decoupling tensor computation from register ownership, revolutionizing GPU efficiency.
Deltoris achieves a staggering 34.2脳 speedup for real-time VLA inference, revolutionizing how embodied AI can operate on edge devices.
Kaleido achieves a remarkable 5.9x speedup in video diffusion transformers by intelligently reusing computations based on latent space correlations.
GF-DiT achieves up to 6.01脳 throughput improvement and 95% latency reduction by dynamically adapting GPU parallelism in response to workload demands.
