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.
LLM Infra Trending Repositories
Explore GitHub Trending repositories tagged “llm-infra”.
Every repository shown here comes from the PostgreSQL Trending catalog.
Ranked by:Stars
Trending Repositories
datawhalechina/llm-algo-leetcode
LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法与系统教程》面向大模型入门到进阶的算法实战教程，覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。
