Search papers, labs, and topics across Lattice.
HIT(SZ)
3
0
8
KernelFlume slashes operational costs by up to 61% while maintaining low latency for long-context LLM decoding, revolutionizing how we scale model serving.
DigenRL achieves up to 2.10x throughput gains for diffusion-based generative LLMs by disaggregating resource allocation and optimizing execution pipelines.
LLM training bottlenecks? ZipCCL achieves up to 1.18x end-to-end speedups by losslessly compressing communication collectives, without sacrificing model quality.
