Alternatives and similar repositories for Block-Attention

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

• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆60Updated 2 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV [NeurIPS 2025]
  ☆120Updated last month
• OpenSparseLLMs / Linear-MoE
  ☆126Updated 6 months ago
• mutonix / pyramidinfer
  ☆49Updated last year
• UNITES-Lab / MC-SMoE
  [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆102Updated 6 months ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆61Updated 10 months ago
• mozhu621 / LongGenBench
  ☆29Updated 2 months ago
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆52Updated last year
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆39Updated 10 months ago
• 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
  ☆69Updated 5 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆282Updated last month
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆24Updated last year
• dvlab-research / Q-LLM
  This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"
  ☆55Updated last year
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆215Updated 6 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆213Updated 10 months ago
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆49Updated 5 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆112Updated 9 months ago
• infinigence / LVEval
  Repository of LV-Eval Benchmark
  ☆73Updated last year
• FasterDecoding / SnapKV
  ☆296Updated 5 months ago
• BaohaoLiao / RSD
  [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
  ☆52Updated 7 months ago
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆38Updated last year
• GeniusHTX / TALE
  ☆140Updated 3 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆159Updated 2 months ago
• Jikai0Wang / OPT-Tree
  ☆29Updated 7 months ago
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆182Updated 5 months ago
• mit-han-lab / fastrl
  [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
  ☆119Updated 3 weeks ago
• Multiverse4FM / Multiverse
  ☆89Updated 6 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆109Updated 9 months ago
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆184Updated 4 months ago