Alternatives and similar repositories for capi

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

• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• google-deepmind / tips
  ☆104Updated 5 months ago
• lucidrains / titok-pytorch
  Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"
  ☆181Updated last year
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆303Updated 2 months ago
• philippe-eecs / vitok
  ☆34Updated 4 months ago
• apple / ml-sigmoid-attention
  ☆302Updated 5 months ago
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆293Updated 11 months ago
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 9 months ago
• dome272 / Flow-Matching
  My take on Flow Matching
  ☆78Updated 8 months ago
• indri-voice / vit.triton
  VIT inference in triton because, why not?
  ☆31Updated last year
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆62Updated this week
• facebookresearch / webssl
  Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).
  ☆185Updated 5 months ago
• facebookresearch / Mixture-of-Transformers
  Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.
  ☆107Updated 3 weeks ago
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆39Updated last week
• facebookresearch / EvalGIM
  🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…
  ☆85Updated 9 months ago
• apple / ml-flextok
  FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
  ☆255Updated 4 months ago
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 6 months ago
• TomerRonen34 / mixed-resolution-vit
  ☆53Updated 2 years ago
• cloneofsimo / min-fsdp
  ☆89Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• goombalab / hydra
  Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"
  ☆159Updated 8 months ago
• riverstone496 / awesome-second-order-optimization
  ☆28Updated this week
• facebookresearch / jepa-intuitive-physics
  This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"
  ☆184Updated 7 months ago
• wmn-231314 / diffusion-data-constraint
  Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…
  ☆98Updated last month
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 9 months ago
• WalBouss / LeGrad
  [ICCV25] Official Implementation of LeGrad
  ☆79Updated 11 months ago
• evanatyourservice / kron_torch
  An implementation of PSGD Kron second-order optimizer for PyTorch
  ☆97Updated 2 months ago
• amorehead / jvp_flash_attention
  Flash Attention Triton kernel with support for second-order derivatives
  ☆94Updated this week
• helblazer811 / ConceptAttention
  ConceptAttention: A method for interpreting multi-modal diffusion transformers.
  ☆332Updated 5 months ago
• lucidrains / multimodal-dit-pytorch
  Implementation of a multimodal diffusion transformer in Pytorch
  ☆105Updated last year