xiayuqing0622 / flex_head_faLinks
Fast and memory-efficient exact attention
☆70Updated 5 months ago
Alternatives and similar repositories for flex_head_fa
Users that are interested in flex_head_fa are comparing it to the libraries listed below
Sorting:
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆84Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆160Updated 2 months ago
- The evaluation framework for training-free sparse attention in LLMs☆90Updated 2 months ago
- ☆81Updated last year
- ☆123Updated 2 months ago
- ☆148Updated 2 years ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 8 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆113Updated 2 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆233Updated 8 months ago
- ☆139Updated 6 months ago
- ☆80Updated 6 months ago
- ☆237Updated 2 months ago
- Stick-breaking attention☆59Updated last month
- Linear Attention Sequence Parallelism (LASP)☆86Updated last year
- Transformers components but in Triton☆34Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 10 months ago
- ☆40Updated 4 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- ☆51Updated 9 months ago
- ☆110Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- Efficient triton implementation of Native Sparse Attention.☆208Updated 3 months ago
- Here we will test various linear attention designs.☆62Updated last year
- Token Omission Via Attention☆128Updated 10 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆241Updated 2 months ago
- 🔥 A minimal training framework for scaling FLA models☆233Updated last week
- Triton implementation of FlashAttention2 that adds Custom Masks.☆132Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆152Updated 4 months ago
- ☆51Updated 2 months ago