microsoft / RetrievalAttentionLinks
Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
☆75Updated last week
Alternatives and similar repositories for RetrievalAttention
Users that are interested in RetrievalAttention are comparing it to the libraries listed below
Sorting:
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆66Updated 2 months ago
- ☆131Updated last month
- ☆113Updated 9 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆176Updated 11 months ago
- ☆68Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆151Updated last year
- A framework for generating realistic LLM serving workloads☆53Updated 2 months ago
- ☆78Updated 4 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆61Updated last week
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- ☆120Updated 10 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆23Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆17Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- ☆54Updated last year
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆52Updated 2 months ago
- A lightweight design for computation-communication overlap.☆157Updated last week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆52Updated 3 weeks ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆66Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆115Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆240Updated 2 months ago
- ☆279Updated last week
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 2 weeks ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆27Updated last year
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 8 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year