Inference Acceleration Trending Repositories

Explore GitHub Trending repositories tagged “inference-acceleration”.

Every repository shown here comes from the PostgreSQL Trending catalog.

Ranked by:Stars
thu-ml/SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Cuda3,652483Built by@jt-zhang@jason-huang03@whx1003@XiaomingXu1995@guilhermeleobas