Alternatives and similar repositories for Block-Attention

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

• OpenSparseLLMs / Linear-MoE
  ☆119Updated 4 months ago
• mozhu621 / LongGenBench
  ☆28Updated 3 weeks ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆106Updated last month
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆56Updated 3 weeks ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆55Updated 8 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆33Updated 8 months ago
• hemingkx / TokenSkip
  [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs
  ☆186Updated 3 months ago
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆52Updated 11 months ago
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆79Updated last week
• UNITES-Lab / MC-SMoE
  [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆96Updated 4 months ago
• mutonix / pyramidinfer
  ☆46Updated 11 months ago
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆65Updated 3 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆158Updated last month
• dvlab-research / Q-LLM
  This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"
  ☆55Updated last year
• infinigence / LVEval
  Repository of LV-Eval Benchmark
  ☆70Updated last year
• FasterDecoding / SnapKV
  ☆284Updated 3 months ago
• horseee / CoT-Valve
  CoT-Valve: Length-Compressible Chain-of-Thought Tuning
  ☆86Updated 8 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆260Updated 3 weeks ago
• zjunlp / LightThinker
  [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
  ☆112Updated 6 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆49Updated last year
• LCLM-Horizon / A-Comprehensive-Survey-For-Long-Context-Language-Modeling
  A Comprehensive Survey on Long Context Language Modeling
  ☆193Updated 3 months ago
• namespace-Pt / UltraGist
  ☆18Updated 10 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆110Updated 7 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆205Updated 8 months ago
• GeniusHTX / TALE
  ☆133Updated last month
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆165Updated last month
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆23Updated last year
• princeton-nlp / ProLong
  Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
  ☆231Updated last month
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆197Updated 4 months ago
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆258Updated 5 months ago