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
  ☆117Updated 2 months ago
• mutonix / pyramidinfer
  ☆45Updated 9 months ago
• UNITES-Lab / MC-SMoE
  [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆92Updated 2 months ago
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆51Updated 10 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆90Updated 2 months ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆52Updated 6 months ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
  ☆49Updated last month
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆48Updated 10 months ago
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆63Updated last month
• dvlab-research / Q-LLM
  This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"
  ☆54Updated last year
• FasterDecoding / SnapKV
  ☆276Updated last month
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆31Updated 6 months ago
• hao-ai-lab / Dynasor
  Simple extension on vLLM to help you speed up reasoning model without training.
  ☆181Updated 3 months ago
• mozhu621 / LongGenBench
  ☆27Updated 6 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆147Updated 3 weeks ago
• hemingkx / TokenSkip
  TokenSkip: Controllable Chain-of-Thought Compression in LLMs
  ☆174Updated 2 months ago
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆39Updated last year
• SalesforceAIResearch / GemFilter
  ☆86Updated 7 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆109Updated 5 months ago
• princeton-nlp / ProLong
  Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
  ☆221Updated 5 months ago
• GeniusHTX / TALE
  ☆128Updated last week
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆73Updated 5 months ago
• Glaciohound / LM-Infinite
  Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
  ☆148Updated 5 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆201Updated 6 months ago
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆248Updated 3 months ago
• UCSB-NLP-Chang / KVLink
  ☆20Updated 4 months ago
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆23Updated 10 months ago
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆41Updated last month
• horseee / CoT-Valve
  CoT-Valve: Length-Compressible Chain-of-Thought Tuning
  ☆84Updated 6 months ago
• namespace-Pt / UltraGist
  ☆18Updated 8 months ago