Dao-AILab / grouped-latent-attentionLinks
☆53Updated this week
Alternatives and similar repositories for grouped-latent-attention
Users that are interested in grouped-latent-attention are comparing it to the libraries listed below
Sorting:
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆115Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆32Updated last month
- 🔥 A minimal training framework for scaling FLA models☆146Updated 3 weeks ago
- Efficient triton implementation of Native Sparse Attention.☆155Updated last week
- 16-fold memory access reduction with nearly no loss☆94Updated 2 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆127Updated this week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆158Updated 3 weeks ago
- Transformers components but in Triton☆33Updated 3 weeks ago
- ☆129Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- ☆70Updated 2 weeks ago
- Fast and memory-efficient exact attention☆68Updated 3 months ago
- Linear Attention Sequence Parallelism (LASP)☆83Updated 11 months ago
- ☆105Updated 9 months ago
- ☆74Updated 3 months ago
- ☆20Updated 3 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆93Updated this week
- DPO, but faster 🚀☆42Updated 5 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- Vocabulary Parallelism☆19Updated 2 months ago
- ☆21Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆75Updated 8 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆216Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆107Updated 2 weeks ago
- ☆49Updated 2 weeks ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆63Updated this week
- ring-attention experiments☆143Updated 7 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Updated last year