microsoft / RetrievalAttentionLinks
Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
☆94Updated last month
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☆73Updated this week
- ☆141Updated 3 months ago
- Stateful LLM Serving☆87Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆188Updated last year
- ☆74Updated last week
- ☆124Updated 11 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆51Updated this week
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆155Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆60Updated 11 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆67Updated 4 months ago
- High performance Transformer implementation in C++.☆138Updated 9 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆47Updated last month
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆61Updated 3 weeks ago
- 16-fold memory access reduction with nearly no loss☆105Updated 7 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆26Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆130Updated last year
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 10 months ago
- A framework for generating realistic LLM serving workloads☆71Updated 2 weeks ago
- ☆136Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆48Updated 2 months ago
- ☆78Updated 6 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆40Updated 7 months ago
- ☆55Updated 4 months ago
- ☆80Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- ☆18Updated 4 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆139Updated last month
- nnScaler: Compiling DNN models for Parallel Training☆117Updated last month
- A lightweight design for computation-communication overlap.☆181Updated 2 weeks ago
- ☆63Updated last month