Alternatives and similar repositories for AdaSkip

Users that are interested in AdaSkip are comparing it to the libraries listed below

• Adaxry / Unified_Layer_Skipping
  ☆14Updated last year
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆47Updated 3 weeks ago
• SqueezeAILab / SqueezedAttention
  SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference
  ☆52Updated 9 months ago
• LLMkvsys / rethink-kv-compression
  ☆17Updated 5 months ago
• Jingyu6 / speculative_prefill
  ☆41Updated 3 months ago
• 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
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆31Updated 6 months ago
• Jikai0Wang / OPT-Tree
  ☆26Updated 3 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆42Updated last year
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆90Updated 2 months ago
• yangyifei729 / KVSharer
  Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''
  ☆28Updated 10 months ago
• Infini-AI-Lab / APE
  ☆33Updated 6 months ago
• metacarbon / shareAtt
  Beyond KV Caching: Shared Attention for Efficient LLMs
  ☆19Updated last year
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆108Updated 4 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆104Updated 5 months ago
• henryzhongsc / longctx_bench
  Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…
  ☆82Updated 6 months ago
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆24Updated last year
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆39Updated last year
• tsinghua-ideal / Twilight
  Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆19Updated 6 months ago
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆36Updated last year
• LiuXiaoxuanPKU / OSD
  ☆56Updated 8 months ago
• NonvolatileMemory / flash_tree_attn
  ☆18Updated 8 months ago
• abdelfattah-lab / TokenButler
  ☆23Updated last month
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆74Updated 5 months ago
• hdong920 / GRIFFIN
  ☆38Updated last year
• Infini-AI-Lab / Sirius
  Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…
  ☆22Updated 11 months ago
• MIRALab-USTC / LLM-AttentionPredictor
  The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Ch…
  ☆17Updated last month
• hdong920 / LESS
  ☆51Updated last year
• pzs19 / TokenSelect
  ☆15Updated 5 months ago