Alternatives and similar repositories for compute-better-spent

Users that are interested in compute-better-spent are comparing it to the libraries listed below

• AndPotap / einsum-search
  ☆32Updated 10 months ago
• lucidrains / pause-transformer
  Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…
  ☆53Updated last year
• cloneofsimo / zeroshampoo
  ☆34Updated 10 months ago
• edwardmilsom / function-space-learning-rates-paper
  Code for the paper "Function-Space Learning Rates"
  ☆23Updated 2 months ago
• lucidrains / gateloop-transformer
  Implementation of GateLoop Transformer in Pytorch and Jax
  ☆89Updated last year
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 8 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆41Updated this week
• berlino / seq_icl
  ☆53Updated last year
• google-deepmind / spectral_ssm
  ☆33Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• epfml / DenseFormer
  ☆81Updated last year
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆81Updated 9 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆85Updated last year
• cloneofsimo / min-fsdp
  ☆83Updated last year
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆102Updated 2 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆149Updated last month
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆80Updated last year
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆123Updated 7 months ago
• LIONS-EPFL / scion
  ☆33Updated 3 weeks ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆66Updated 10 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆40Updated last year
• nikhilvyas / SOAP
  ☆206Updated 8 months ago
• ruke1ire / RTF
  A State-Space Model with Rational Transfer Function Representation.
  ☆79Updated last year
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆88Updated last year
• insuhan / hyper-attn
  ☆81Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• AhmedImtiazPrio / grok-adversarial
  Deep Networks Grok All the Time and Here is Why
  ☆37Updated last year
• machine-discovery / deer
  Parallelizing non-linear sequential models over the sequence length
  ☆53Updated last month
• sustcsonglin / mamba-triton
  ☆49Updated last year