How Triton Compiler Works Under the Hood!

Enough MLIR to be dangerous - how Triton uses MLIR passes to progressively lower IR

Improve model to reduce duplicates and improve training performance

Exploring a simple transformer model for sequence modelling in recommender systems

What happens when triton.compile is called in the frontend?

Missing tutorial on how triton program gets converted to cuda kernels under the hood

Benchmarking our own GPT2 model against Huggingface GPT2 model

Writing GPT2 from scratch and assigning weights from pre-trained Huggingface model

Another article in the wild on writing transformers from scratch

Performance focussed talk on using torch.compile to generate fused kernels and learning triton along the way

Train LSTM on Animal Farm and create new text

Use convolutional neural networks for image compression

Use transfer learning on VGG-16 to detect dog breeds

Train a Convolutional Neural Network to Detect Dog Breeds

How to Solve the Dynamic Discovery Problem in ZeroMQ