mit-han-lab / duo-attention
[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
☆442Updated last month
Alternatives and similar repositories for duo-attention:
Users that are interested in duo-attention are comparing it to the libraries listed below
- ☆233Updated 11 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆284Updated 2 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆388Updated 4 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆337Updated 7 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆265Updated 4 months ago
- Efficient LLM Inference over Long Sequences☆365Updated last month
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆149Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆463Updated 2 weeks ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆245Updated last week
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆359Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆301Updated 9 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆170Updated last week
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆123Updated 3 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆433Updated 8 months ago
- LLM KV cache compression made easy☆444Updated 2 weeks ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆139Updated 3 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 4 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆155Updated 9 months ago
- Ring attention implementation with flash attention☆721Updated last month
- A sparse attention kernel supporting mix sparse patterns☆169Updated last month
- A family of compressed models obtained via pruning and knowledge distillation☆331Updated 4 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆89Updated 2 weeks ago
- KV cache compression for high-throughput LLM inference☆119Updated last month
- ☆122Updated last month
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆368Updated 4 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆624Updated 3 weeks ago
- TransMLA: Multi-Head Latent Attention Is All You Need☆221Updated last month
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆177Updated last month