OpenMachine-ai / transformer-tricksLinks
A collection of tricks and tools to speed up transformer models
☆187Updated 2 weeks ago
Alternatives and similar repositories for transformer-tricks
Users that are interested in transformer-tricks are comparing it to the libraries listed below
Sorting:
- ☆65Updated 7 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆206Updated 5 months ago
- ☆253Updated 5 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆367Updated 2 months ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆162Updated 7 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆207Updated last week
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- Work in progress.☆75Updated 4 months ago
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning☆244Updated 2 weeks ago
- The evaluation framework for training-free sparse attention in LLMs☆102Updated last month
- RWKV-7: Surpassing GPT☆100Updated 11 months ago
- ☆60Updated 6 months ago
- ☆57Updated last year
- FlashRNN - Fast RNN Kernels with I/O Awareness☆144Updated 3 weeks ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 11 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆223Updated last week
- ☆106Updated 5 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated last year
- Memory optimized Mixture of Experts☆69Updated 3 months ago
- ☆96Updated 8 months ago
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆59Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- ☆146Updated 11 months ago
- Efficient triton implementation of Native Sparse Attention.☆247Updated 5 months ago
- ☆130Updated 5 months ago
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆53Updated 8 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆333Updated 8 months ago
- Normalized Transformer (nGPT)☆192Updated 11 months ago
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆109Updated 2 years ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 9 months ago