← Sai Rohith Tanuku's projects
@rohith1125by Sai Rohith Tanuku · IBM
Pythonattention-mechanismautogradcudadeep-learningmachine-learning
encoder-in-cuda
Transformer Encoder Block from scratch in pure NumPy — no PyTorch, no TensorFlow. Hand-written attention, layernorm, GELU, autograd engine, and CUDA kernel simulations.
More from members
All projectsSee what other members are building and what each project is looking for.
Comments · 0