Alternatives and similar repositories for Block-Attention

Users that are interested in Block-Attention are comparing it to the libraries listed below

• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆116Updated last week
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆52Updated last year
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆68Updated 4 months ago
• mozhu621 / LongGenBench
  ☆29Updated 2 months ago
• OpenSparseLLMs / Linear-MoE
  ☆120Updated 6 months ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆60Updated 9 months ago
• mutonix / pyramidinfer
  ☆49Updated last year
• FasterDecoding / SnapKV
  ☆290Updated 4 months ago
• UNITES-Lab / MC-SMoE
  [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆99Updated 5 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆38Updated 9 months ago
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆209Updated 6 months ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆59Updated 2 months ago
• ZhenweiAn / Dynamic_MoE
  Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"
  ☆66Updated last year
• LCLM-Horizon / A-Comprehensive-Survey-For-Long-Context-Language-Modeling
  A Comprehensive Survey on Long Context Language Modeling
  ☆209Updated last week
• Jingyu6 / speculative_prefill
  ☆47Updated 6 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆212Updated 9 months ago
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆180Updated 3 months ago
• princeton-nlp / ProLong
  Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
  ☆240Updated 2 months ago
• Glaciohound / LM-Infinite
  Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
  ☆152Updated 8 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• Infini-AI-Lab / Multiverse
  ☆104Updated 2 months ago
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆37Updated last year
• hemingkx / TokenSkip
  [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs
  ☆193Updated this week
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆24Updated last year
• infinigence / LVEval
  Repository of LV-Eval Benchmark
  ☆72Updated last year
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆42Updated last year
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆175Updated 2 months ago
• SkyworkAI / skywork-o1-prm-inference
  ☆65Updated last year
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆48Updated 4 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆155Updated last month