Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
Speculative decoding drafters can achieve over 2x speedup on 256K context by treating distant tokens as shared far memory with sharpened attention.
Achieving up to 19x performance improvements on resource-constrained workloads by harnessing the power of GPUs could redefine how we approach software efficiency.