mit-han-lab / duo-attention
[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
☆453Updated 2 months ago
Alternatives and similar repositories for duo-attention:
Users that are interested in duo-attention are comparing it to the libraries listed below
- ☆237Updated 11 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆288Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆273Updated 5 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆391Updated 5 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆340Updated 8 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆477Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 9 months ago
- Efficient LLM Inference over Long Sequences☆370Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆184Updated last week
- Ring attention implementation with flash attention☆743Updated 2 weeks ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆388Updated 2 weeks ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆146Updated this week
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆158Updated 10 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆123Updated 4 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆643Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆97Updated this week
- EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆263Updated 6 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆352Updated last year
- scalable and robust tree-based speculative decoding algorithm☆343Updated 2 months ago
- A sparse attention kernel supporting mix sparse patterns☆197Updated 2 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆161Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆258Updated this week
- Explorations into some recent techniques surrounding speculative decoding☆259Updated 4 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆379Updated 5 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆404Updated 6 months ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆162Updated 3 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆304Updated 2 weeks ago
- ☆122Updated 2 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆334Updated 5 months ago