OpenNLPLab / lightning-attentionLinks
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
☆313Updated 4 months ago
Alternatives and similar repositories for lightning-attention
Users that are interested in lightning-attention are comparing it to the libraries listed below
Sorting:
- TransMLA: Multi-Head Latent Attention Is All You Need☆310Updated this week
- Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels☆106Updated last year
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆170Updated last year
- 🔥 A minimal training framework for scaling FLA models☆170Updated last week
- Official implementation of TransNormerLLM: A Faster and Better LLM☆245Updated last year
- The official implementation of Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)☆375Updated this week
- Low-bit optimizers for PyTorch☆128Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆209Updated last week
- ☆191Updated last year
- DeepSeek Native Sparse Attention pytorch implementation☆71Updated 3 months ago
- Efficient triton implementation of Native Sparse Attention.☆168Updated last month
- ☆151Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆519Updated last month
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆101Updated last year
- The official implementation of the EMNLP 2023 paper LLM-FP4☆207Updated last year
- When it comes to optimizers, it's always better to be safe than sorry☆241Updated 2 months ago
- ☆105Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆702Updated 3 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆176Updated this week
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆163Updated last year
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆422Updated last month
- ☆286Updated 2 months ago
- A quantization algorithm for LLM☆141Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆519Updated 3 weeks ago
- Implementation of "Attention Is Off By One" by Evan Miller☆193Updated last year
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆71Updated 3 weeks ago
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆158Updated 2 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆221Updated last month
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆133Updated last year