Alternatives and similar repositories for transformer-tricks

Users that are interested in transformer-tricks are comparing it to the libraries listed below

• kyleliang919 / Super_Muon
  ☆66Updated 9 months ago
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆394Updated 6 months ago
• BlinkDL / modded-nanogpt-rwkv
  RWKV-7: Surpassing GPT
  ☆102Updated last year
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆404Updated 3 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆223Updated 6 months ago
• HanGuo97 / log-linear-attention
  ☆260Updated 6 months ago
• Dao-AILab / grouped-latent-attention
  ☆133Updated 6 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆106Updated 2 months ago
• Jellyfish042 / Sudoku-RWKV
  ☆148Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆194Updated last year
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆131Updated last year
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆198Updated 3 weeks ago
• woct0rdho / transformers-qwen3-moe-fused
  Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
  ☆217Updated this week
• IST-DASLab / QuEST
  Work in progress.
  ☆75Updated last month
• sustcsonglin / linear-attention-and-beyond-slides
  ☆101Updated 10 months ago
• BorealisAI / neuzip
  Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…
  ☆60Updated last year
• deepreinforce-ai / CUDA-L1
  CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
  ☆277Updated last month
• tridao / flash-attention-wheels
  ☆59Updated 2 years ago
• NVlabs / QeRL
  QeRL enables RL for 32B LLMs on a single H100 GPU.
  ☆470Updated last month
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆226Updated last month
• HazyResearch / lolcats
  Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
  ☆249Updated 10 months ago
• amazon-science / mxfp4-llm
  Official implementation for Training LLMs with MXFP4
  ☆116Updated 8 months ago
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆219Updated 9 months ago
• DeepAuto-AI / hip-attention
  Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
  ☆148Updated last month
• IST-DASLab / Quartet
  ☆113Updated last month
• itsnamgyu / block-transformer
  Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)
  ☆162Updated 8 months ago
• wdlctc / headinfer
  ☆63Updated 7 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆256Updated 7 months ago
• tilde-research / MoMoE-impl
  Memory optimized Mixture of Experts
  ☆72Updated 5 months ago
• sgl-project / sgl-cookbook
  Cookbook of SGLang - Recipe
  ☆45Updated this week