[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
132,241 visible repositories in the index
1–4 of 4 · Most stars
[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.
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.