Alternatives and similar repositories for duo-attention

Users that are interested in duo-attention are comparing it to the libraries listed below

• FasterDecoding / SnapKV
  ☆284Updated 3 months ago
• jy-yuan / KIVI
  [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
  ☆329Updated last month
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆158Updated last month
• SqueezeAILab / KVQuant
  [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  ☆389Updated last year
• NVIDIA / Star-Attention
  Efficient LLM Inference over Long Sequences
  ☆390Updated 4 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆338Updated 3 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆242Updated 2 months ago
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆604Updated this week
• Infini-AI-Lab / MagicPIG
  [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
  ☆238Updated 10 months ago
• hao-ai-lab / Consistency_LLM
  [ICML 2024] CLLMs: Consistency Large Language Models
  ☆405Updated 11 months ago
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆197Updated 4 months ago
• NVIDIA / kvpress
  LLM KV cache compression made easy
  ☆660Updated last week
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆147Updated 3 months ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆191Updated 3 weeks ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆147Updated 2 weeks ago
• FMInference / H2O
  [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
  ☆482Updated last year
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆142Updated 8 months ago
• hemingkx / Spec-Bench
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆324Updated 6 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆169Updated last year
• mit-han-lab / x-attention
  [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆239Updated 3 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆143Updated 8 months ago
• NVlabs / Minitron
  A family of compressed models obtained via pruning and knowledge distillation
  ☆354Updated 11 months ago
• FasterDecoding / TEAL
  ☆145Updated 8 months ago
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆320Updated last year
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆439Updated this week
• October2001 / Awesome-KV-Cache-Compression
  📰 Must-read papers on KV Cache Compression (constantly updating 🤗).
  ☆566Updated 3 weeks ago
• thunlp / InfLLM
  The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…
  ☆382Updated last year
• OpenGVLab / EfficientQAT
  [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆308Updated 5 months ago
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆582Updated last week
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆174Updated last year