MayDomine / Burst-AttentionLinks
Distributed IO-aware Attention algorithm
☆21Updated last week
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☆77Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆215Updated last year
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- ☆55Updated last week
- An easy-to-use package for implementing SmoothQuant for LLMs☆106Updated 6 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.☆17Updated last year
- ☆20Updated 5 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆129Updated 4 months ago
- Training library for Megatron-based models☆109Updated this week
- Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.☆102Updated 2 weeks ago
- An industrial extension library of pytorch to accelerate large scale model training☆50Updated last month
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- ☆78Updated 5 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆210Updated 3 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆152Updated last month
- ☆147Updated 7 months ago
- Vocabulary Parallelism☆23Updated 6 months ago
- ☆95Updated 6 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆141Updated last month
- ☆200Updated 5 months ago