🎯
Focusing
PhD Student @ucsb | Ex - @amazon-science, @google | Kaggle Grandmaster @Kaggle | Ex - BUET | Ex - @wandb
- California, USA
- https://awsaf49.github.io
- https://www.kaggle.com/awsaf49
- in/awsaf49
- @awsaf49
Highlights
- Pro
Lists (3)
Sort Name ascending (A-Z)
Starred repositories
1
star
written in Cuda
Clear filter
[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.