xiayuqing0622 / flex_head_fa
Fast and memory-efficient exact attention
☆67Updated 3 weeks 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
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆58Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆125Updated 3 months ago
- Efficient triton implementation of Native Sparse Attention.☆116Updated this week
- ☆81Updated last year
- Linear Attention Sequence Parallelism (LASP)☆79Updated 9 months ago
- ☆63Updated 3 weeks ago
- ☆116Updated last month
- Stick-breaking attention☆48Updated last week
- Triton-based implementation of Sparse Mixture of Experts.☆208Updated 3 months ago
- 🔥 A minimal training framework for scaling FLA models☆82Updated this week
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆122Updated 7 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆102Updated 7 months ago
- ☆140Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆62Updated this week
- ☆19Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆81Updated this week
- Transformers components but in Triton☆32Updated this week
- Code for studying the super weight in LLM☆94Updated 3 months ago
- ☆49Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆110Updated 3 months ago
- ☆36Updated 6 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆102Updated this week
- Simple and efficient pytorch-native transformer training and inference (batched)☆71Updated 11 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 5 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- Cascade Speculative Drafting☆29Updated 11 months ago
- ☆70Updated last week
- ☆51Updated 10 months ago