SparseRefine is a novel approach that enhances dense low-resolution predictions with sparse high-resolution refinements. It achieves significant speedup: 1.5 to 3.7 times when applied to HRNet-W48, SegFormer-B5, Mask2Former-T/L and SegNeXt-L on Cityscapes, with negligible to no loss of accuracy.

A training-free algorithm to harness multiple GPUs to accelerate diffusion model inference without sacrificing image quality.

Quest is an effient long-context LLM inference framework that leverages query-aware sparsity in KV cache to reduce memory movement during attention and thus boost throughput.

We enable LLMs to work on infinite-length texts without compromising efficiency and performance.

LongLoRA takes advantage of shifted sparse attention to greatly reduce the finetuning cost of long context LLMs.

This TinyML project aims to enable efficient AI computing on the edge by innovating model compression techniques as well as high-performance system design.