Alternatives and similar repositories for abnormal-floats

Users that are interested in abnormal-floats are comparing it to the libraries listed below

• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆73Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆47Updated last year
• Ryu1845 / hyena-jax
  Implementation of Hyena Hierarchy in JAX
  ☆10Updated 2 years ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆79Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated last year
• sustcsonglin / mamba-triton
  ☆48Updated last year
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆45Updated last year
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆78Updated last year
• berlino / seq_icl
  ☆53Updated last year
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆61Updated last year
• insuhan / hyper-attn
  ☆83Updated last year
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆38Updated 5 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• 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…
  ☆52Updated 2 years ago
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆127Updated last year
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆17Updated last year
• BlinkDL / SmallInitEmb
  LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence
  ☆60Updated 3 years ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …
  ☆60Updated last year
• cat-state / tinypar
  ☆20Updated 2 years ago
• epfml / schedules-and-scaling
  Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"
  ☆85Updated last year
• cloneofsimo / min-fsdp
  ☆91Updated last year
• HazyResearch / prefix-linear-attention
  ☆57Updated last year
• shikaiqiu / compute-better-spent
  ☆61Updated last year
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated last year
• sustcsonglin / gated_linear_attention_layer
  ☆31Updated last year
• samblouir / birdie
  ☆13Updated 5 months ago
• renll / SeqBoat
  [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling
  ☆39Updated last year
• RobertCsordas / moe_layer
  sigma-MoE layer
  ☆20Updated last year
• kyo-takano / chinchilla
  A toolkit for scaling law research ⚖
  ☆53Updated 9 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year