microsoft / RetrievalAttentionLinks
Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
☆83Updated 2 weeks ago
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☆71Updated last week
- ☆138Updated 2 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆184Updated last year
- ☆72Updated last year
- ☆122Updated 10 months ago
- Stateful LLM Serving☆85Updated 6 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆62Updated 3 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 11 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆154Updated last year
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆58Updated this week
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆94Updated last week
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆26Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆37Updated 7 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆41Updated last week
- ☆78Updated 5 months ago
- A framework for generating realistic LLM serving workloads☆65Updated last week
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 9 months ago
- ☆56Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- ☆77Updated 11 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- ☆17Updated 4 months ago
- ☆18Updated 3 months ago
- High performance Transformer implementation in C++.☆134Updated 8 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 2 months ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆30Updated 4 months ago
- ☆131Updated 11 months ago
- ☆300Updated this week
- ☆51Updated 3 months ago
- A lightweight design for computation-communication overlap.☆177Updated 2 weeks ago