Pinned Loading

1. TinyML-and-Efficient-Deep-Learning-Computing TinyML-and-Efficient-Deep-Learning-Computing Public

   This course tackles the real problems ML engineers face every day

   Jupyter Notebook 2

2. transformer_problems transformer_problems Public

   A practical guide to the 18 biggest limitations of transformer architectures — and how researchers are fixing them.

   Jupyter Notebook 1

3. pytorch/pytorch pytorch/pytorch Public

   Tensors and Dynamic neural networks in Python with strong GPU acceleration

   Python 102k 28.6k

4. pytorch_tutorial pytorch_tutorial Public

   Complete PyTorch Tutorial Series — From Absolute Beginner to Production-Ready

   Jupyter Notebook

5. Transformer Transformer Public

   A Transformer is a neural network architecture for sequence modeling that uses self-attention instead of recurrence. It consists of stacked layers of multi-head self-attention, feed-forward network…

   Shell

6. Paged-Attention Paged-Attention Public

   Efficient memory management for Large Language Model (LLM) inference using block-based KV cache.

   Python