Alternatives and similar repositories for awesome-second-order-optimization

Users that are interested in awesome-second-order-optimization are comparing it to the libraries listed below

• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆63Updated last month
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆102Updated last month
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 11 months ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆85Updated last year
• shikaiqiu / compute-better-spent
  ☆61Updated last year
• facebookresearch / capi
  Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"
  ☆123Updated 7 months ago
• CLAIRE-Labo / flash_attention
  A basic pure pytorch implementation of flash attention
  ☆16Updated last year
• kvfrans / splus
  ☆119Updated 5 months ago
• nikhilvyas / SOAP
  ☆223Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆173Updated 4 months ago
• microsoft / dion
  Dion optimizer algorithm
  ☆384Updated this week
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• zaydzuhri / softpick-attention
  Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"
  ☆85Updated 2 months ago
• evanatyourservice / kron_torch
  An implementation of PSGD Kron second-order optimizer for PyTorch
  ☆97Updated 3 months ago
• sustcsonglin / linear-attention-and-beyond-slides
  ☆95Updated 8 months ago
• modula-systems / modula
  🧱 Modula software package
  ☆303Updated 3 months ago
• HanGuo97 / log-linear-attention
  ☆254Updated 5 months ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆68Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆192Updated last year
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆23Updated 5 months ago
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆326Updated last week
• willisma / diffuse_nnx
  A comprehensive JAX/NNX library for diffusion and flow matching generative algorithms, featuring DiT (Diffusion Transformer) and its vari…
  ☆116Updated last month
• wmn-231314 / diffusion-data-constraint
  Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…
  ☆108Updated 3 weeks ago
• LIONS-EPFL / scion
  ☆47Updated last month
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• amorehead / jvp_flash_attention
  Flash Attention Triton kernel with support for second-order derivatives
  ☆112Updated last month
• young-geng / scalax
  A simple library for scaling up JAX programs
  ☆144Updated 2 weeks ago
• srush / mamba-primer
  ☆38Updated last year
• google-deepmind / md4
  Official Jax Implementation of MD4 Masked Diffusion Models
  ☆144Updated 8 months ago