[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.
- attention
- inference-acceleration
- llm
- quantization
Repository Index
70,234 visible repositories in the index
1–3 of 3 · Most stars
This package contains the original 2012 AlexNet code.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel