Skip to content

@midjourney Midjourney

Change the repository type filter

All

    Repositories list

    14 repositories

    • docs

      Public
      (deprecated) Source for Midjourney's official wiki
      CSS
      •70•389•2•0•Updated Nov 24, 2025Nov 24, 2025

    • SageAttention

      Public
      Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.
      Cuda
      •
      Apache License 2.0
      •289•0•0•0•Updated Jul 8, 2025Jul 8, 2025

    • xDiT

      Public
      xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
      Python
      •
      Apache License 2.0
      •295•0•0•0•Updated Jun 18, 2025Jun 18, 2025

    • long-context-attention

      Public
      USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
      Python
      •
      Apache License 2.0
      •74•0•0•0•Updated Jun 5, 2025Jun 5, 2025

    • flash-attention-jax

      Public
      Implementation of Flash Attention in Jax
      Python
      •
      MIT License
      •24•8•0•0•Updated Jul 17, 2024Jul 17, 2024

    • nanobind

      Public
      nanobind: tiny and efficient C++/Python bindings
      C++
      •
      BSD 3-Clause "New" or "Revised" License
      •271•1•0•0•Updated Mar 15, 2024Mar 15, 2024

    • hf-transformers

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •32k•4•0•0•Updated Feb 14, 2024Feb 14, 2024

    • transformers

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •32k•56•0•0•Updated Sep 1, 2023Sep 1, 2023

    • jaxtorch

      Public
      Python
      •
      MIT License
      •10•0•0•0•Updated Jun 7, 2023Jun 7, 2023

    • equinox

      Public archive
      Elegant easy-to-use neural networks in JAX. https://docs.kidger.site/equinox/
      Python
      •
      Apache License 2.0
      •177•0•0•0•Updated May 1, 2023May 1, 2023

    • einops

      Public
      Deep learning operations reinvented (for pytorch, tensorflow, jax and others)
      Python
      •
      MIT License
      •390•6•0•0•Updated Dec 29, 2022Dec 29, 2022

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •2.2k•3•0•0•Updated Dec 17, 2022Dec 17, 2022

    • jax

      Public archive
      Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
      Python
      •
      Apache License 2.0
      •3.3k•13•0•0•Updated Oct 12, 2022Oct 12, 2022

    • flax

      Public archive
      Flax is a neural network library for JAX that is designed for flexibility.
      Python
      •
      Apache License 2.0
      •769•9•0•0•Updated Sep 17, 2022Sep 17, 2022