Alternatives and similar repositories for manifolds

Users that are interested in manifolds are comparing it to the libraries listed below

• edwardmilsom / function-space-learning-rates-paper

  View on GitHub
  Code for the paper "Function-Space Learning Rates"
  ☆25Jun 3, 2025Updated 8 months ago
• ethansmith2000 / TransformerExperiments

  View on GitHub
  ☆19Dec 4, 2025Updated 2 months ago
• bentherien / mu_learned_optimization

  View on GitHub
  [Oral; Neurips OPT2024 ] μLO: Compute-Efficient Meta-Generalization of Learned Optimizers
  ☆14Mar 18, 2025Updated 10 months ago
• glassroom / heinsen_attention

  View on GitHub
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Jun 6, 2024Updated last year
• AndPotap / einsum-search

  View on GitHub
  ☆33Oct 4, 2024Updated last year
• packquickly / schedule_free_optx

  View on GitHub
  Schedule free optimiser implemented in JAX using Optimistix
  ☆15May 29, 2024Updated last year
• centralflows / centralflows

  View on GitHub
  Code for implementing central flows
  ☆42Sep 5, 2025Updated 5 months ago
• GindaChen / FlexFlashAttention3

  View on GitHub
  FlexAttention w/ FlashAttention3 Support
  ☆27Oct 5, 2024Updated last year
• proger / nanokitchen

  View on GitHub
  Parallel Associative Scan for Language Models
  ☆18Jan 8, 2024Updated 2 years ago
• sjelassi / transformers_ssm_copy

  View on GitHub
  ☆35Feb 26, 2024Updated last year
• mgmalek / efficient_cross_entropy

  View on GitHub
  ☆124May 28, 2024Updated last year
• yikangshen / megablocks

  View on GitHub
  ☆20May 30, 2024Updated last year
• kyleliang919 / Super_Muon

  View on GitHub
  ☆67Mar 21, 2025Updated 10 months ago
• smonsays / hypernetwork-attention

  View on GitHub
  Official code for the paper "Attention as a Hypernetwork"
  ☆47Jun 22, 2024Updated last year
• HazyResearch / train-tk

  View on GitHub
  train with kittens!
  ☆63Oct 25, 2024Updated last year
• IBM / triton-dejavu

  View on GitHub
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆96Sep 19, 2025Updated 4 months ago
• Aleph-Alpha-Research / NeurIPS-WANT-submission-efficient-parallelization-layouts

  View on GitHub
  ☆22Dec 15, 2023Updated 2 years ago
• PKU-ML / LongPPL

  View on GitHub
  Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"
  ☆109Oct 11, 2025Updated 4 months ago
• cloneofsimo / minDinoV2

  View on GitHub
  ☆23Oct 15, 2024Updated last year
• jbaron34 / torchwindow

  View on GitHub
  Display tensors directly from GPU
  ☆11Oct 12, 2025Updated 4 months ago
• Eliyas0007 / Pytorch-Intention

  View on GitHub
  Unofficial implementation of paper : Exploring the Space of Key-Value-Query Models with Intention
  ☆12May 24, 2023Updated 2 years ago
• suzukimain / auto_diffusers

  View on GitHub
  diffusers with search engine
  ☆12Jan 13, 2026Updated last month
• Doraemonzzz / nanoTransNormer

  View on GitHub
  ☆11Oct 11, 2023Updated 2 years ago
• graphcore-research / jax-scalify

  View on GitHub
  JAX Scalify: end-to-end scaled arithmetics
  ☆18Oct 30, 2024Updated last year
• JonasGeiping / linear_cross_entropy_loss

  View on GitHub
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆75Aug 2, 2024Updated last year
• cloneofsimo / min-max-in-dit

  View on GitHub
  ☆27May 3, 2024Updated last year
• iwiwi / epochraft

  View on GitHub
  Checkpointable dataset utilities for foundation model training
  ☆32Jan 29, 2024Updated 2 years ago
• feifeibear / Odysseus-Transformer

  View on GitHub
  Odysseus: Playground of LLM Sequence Parallelism
  ☆79Jun 17, 2024Updated last year
• epfml / schedules-and-scaling

  View on GitHub
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆89Oct 30, 2024Updated last year
• habanero-lab / APPy

  View on GitHub
  APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…
  ☆30Jan 28, 2026Updated 2 weeks ago
• dangxingyu / rnn-icrag

  View on GitHub
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆27Apr 17, 2024Updated last year
• proger / accelerated-scan

  View on GitHub
  Accelerated First Order Parallel Associative Scan
  ☆196Jan 7, 2026Updated last month
• srush / triton-autodiff

  View on GitHub
  Experiment of using Tangent to autodiff triton
  ☆82Jan 22, 2024Updated 2 years ago
• dayal-kalra / low-memory-adam

  View on GitHub
  ☆14Mar 2, 2025Updated 11 months ago
• bdusell / stack-attention

  View on GitHub
  Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"
  ☆18Mar 15, 2024Updated last year
• theAdamColton / ijepa-enhanced

  View on GitHub
  recipe for training fully-featured self supervised image jepa models
  ☆12Jun 4, 2025Updated 8 months ago
• cloneofsimo / ptar

  View on GitHub
  ☆13Jun 3, 2024Updated last year
• nikhilvyas / SOAP_MUON

  View on GitHub
  Combining SOAP and MUON
  ☆19Feb 11, 2025Updated last year
• stanford-futuredata / stk

  View on GitHub
  ☆115Aug 26, 2024Updated last year