MayDomine / Burst-AttentionLinks
Distributed IO-aware Attention algorithm
☆21Updated last month
Alternatives and similar repositories for Burst-Attention
Users that are interested in Burst-Attention are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- ☆69Updated this week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 7 months ago
- ☆20Updated 6 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆107Updated 6 months ago
- Vocabulary Parallelism☆23Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- ☆130Updated 4 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- Sequence-level 1F1B schedule for LLMs.☆18Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆125Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆84Updated last year
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated 2 months ago
- ☆148Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- ☆205Updated 5 months ago
- ☆145Updated 8 months ago
- ☆121Updated last year
- KV cache compression for high-throughput LLM inference☆142Updated 8 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆210Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆242Updated 2 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆144Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 7 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆282Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 6 months ago
- Low-bit optimizers for PyTorch☆132Updated 2 years ago
- ☆48Updated last year
- ☆78Updated 6 months ago