gpu-mode / awesomeMLSys
An ML Systems Onboarding list
☆540Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for awesomeMLSys
- GPU programming related news and material links☆1,208Updated last month
- Puzzles for learning Triton☆1,089Updated last month
- UNet diffusion model in pure CUDA☆567Updated 4 months ago
- Slides, notes, and materials for the workshop☆305Updated 5 months ago
- High Quality Resources on GPU Programming/Architecture☆563Updated 3 months ago
- Building blocks for foundation models.☆388Updated 10 months ago
- The Tensor (or Array)☆408Updated 3 months ago
- The Multilayer Perceptron Language Model☆521Updated 3 months ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆711Updated last month
- Alex Krizhevsky's original code from Google Code☆188Updated 8 years ago
- What would you do with 1000 H100s...☆895Updated 10 months ago
- The Autograd Engine☆530Updated 2 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆479Updated 2 weeks ago
- Tile primitives for speedy kernels☆1,643Updated this week
- ☆388Updated 3 weeks ago
- Flash Attention in ~100 lines of CUDA (forward pass only)☆615Updated 7 months ago
- nanoGPT style version of Llama 3.1☆1,231Updated 3 months ago
- NanoGPT (124M) quality in 7.8 8xH100-minutes☆965Updated this week
- Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆167Updated 3 months ago
- A bibliography and survey of the papers surrounding o1☆643Updated this week
- LLM papers I'm reading, mostly on inference and model compression☆691Updated 10 months ago
- Best practices & guides on how to write distributed pytorch training code☆279Updated last week
- ☆515Updated 2 weeks ago
- Puzzles for exploring transformers☆323Updated last year
- Material for gpu-mode lectures☆2,967Updated this week
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,190Updated this week
- An implementation of the transformer architecture onto an Nvidia CUDA kernel☆157Updated last year
- This repo has all the basic things you'll need in-order to understand complete vision transformer architecture and its various implementa…☆169Updated last month
- ☆133Updated 9 months ago
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆601Updated last week