Alternatives and similar repositories for RetrievalAttention

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

• HugoZHL / PQCache
  [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference
  ☆73Updated last week
• YaoJiayi / CacheBlend
  ☆150Updated 4 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆88Updated 8 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆191Updated last year
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆63Updated last year
• hao-ai-lab / MuxServe
  ☆77Updated last month
• snu-comparch / InfiniGen
  InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)
  ☆160Updated last year
• LoongServe / LoongServe
  ☆124Updated last year
• xinhao-luo / ClusterFusion
  [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
  ☆48Updated last month
• amazon-science / piperag
  PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
  ☆27Updated last year
• pku-liang / ArkVale
  ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)
  ☆44Updated 11 months ago
• tsinghua-ideal / Twilight
  [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning
  ☆65Updated last week
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆68Updated 5 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆48Updated 3 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆106Updated 7 months ago
• microsoft / chunk-attention
  ☆81Updated 7 months ago
• eddiegaoo / Apt-Serve
  ☆18Updated 5 months ago
• alibaba / ServeGen
  A framework for generating realistic LLM serving workloads
  ☆79Updated last month
• microsoft / tokenweave
  Efficient Compute-Communication Overlap for Distributed LLM Inference
  ☆62Updated 2 weeks ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆87Updated 5 months ago
• d-matrix-ai / keyformer-llm
  ☆58Updated last year
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆141Updated 10 months ago
• ruipeterpan / marconi
  Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
  ☆45Updated 8 months ago
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆288Updated 5 months ago
• zcli-charlie / Awesome-KV-Cache
  ☆82Updated last year
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆257Updated last month
• fpgasystems / Chameleon-RAG-Acceleration
  ☆19Updated 5 months ago
• alibaba-edu / qwen-bailian-usagetraces-anon
  ☆57Updated 2 weeks ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆93Updated 2 years ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆78Updated this week