kvfrans / jax-diffusion-transformerLinks
Implementation of Diffusion Transformer (DiT) in JAX
☆276Updated 11 months ago
Alternatives and similar repositories for jax-diffusion-transformer
Users that are interested in jax-diffusion-transformer are comparing it to the libraries listed below
Sorting:
- ☆267Updated 10 months ago
- For optimization algorithm research and development.☆518Updated this week
- Annotated version of the Mamba paper☆482Updated last year
- UNet diffusion model in pure CUDA☆605Updated 11 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆544Updated this week
- Universal Tensor Operations in Einstein-Inspired Notation for Python.☆374Updated last month
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆281Updated 2 months ago
- Accelerated First Order Parallel Associative Scan☆180Updated 9 months ago
- 🧱 Modula software package☆194Updated 2 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆91Updated 2 months ago
- Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs☆380Updated last month
- ☆116Updated last week
- Flow-matching algorithms in JAX☆91Updated 9 months ago
- Normalized Transformer (nGPT)☆181Updated 6 months ago
- A simple implimentation of Bayesian Flow Networks (BFN)☆240Updated last year
- Efficient optimizers☆206Updated this week
- Simple and readable code for training and sampling from diffusion models☆503Updated 4 months ago
- supporting pytorch FSDP for optimizers☆79Updated 5 months ago
- ☆182Updated 5 months ago
- The Tensor (or Array)☆433Updated 9 months ago
- WIP☆93Updated 9 months ago
- A simple library for scaling up JAX programs☆136Updated 7 months ago
- ☆301Updated 11 months ago
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆131Updated 6 months ago
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆117Updated 7 months ago
- seqax = sequence modeling + JAX☆155Updated last month
- ☆88Updated last year
- Library for reading and processing ML training data.☆447Updated this week
- jax-triton contains integrations between JAX and OpenAI Triton☆392Updated this week
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds☆237Updated 3 months ago