Hi, Alex ๐
alexdremov.me
๐ MIPT alumnus โ graduated with honors in PSAMI Informatics and Computational Technologies.
๐จ๐ญ EPFL student โ current Master's in Data Science student
- Compute-Optimal Quantization-Aware Training โ Aleksandr Dremov, David Grangier, Angelos Katharopoulos, Awni Hannun
ICLR 2026 - Training dynamics of the cooldown stage in warmup-stable-decay learning rate scheduler โ Aleksandr Dremov, Alexander Hรคgele, Atli Kosson, Martin Jaggi
TMLR, J2C Certification (ICLR 2026)
- ๐ฅ Understanding Flash Attention: Writing the Algorithm from Scratch in Triton
- ๐ฎ Speed Up PyTorch With Custom Kernels. But It Gets Progressively Darker
- ๐ฅ Simple Ways to Speed Up Your PyTorch Model Training
- ๐ Swift Actors โ Common Problems and Tips
- โค๏ธ I Contributed to PyTorch. Here's What I Learned
| Aleksandr Dremov | @aldrmv | alex@alexdremov.me |





