microsoft / RetrievalAttentionLinks
Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
☆122Updated 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☆83Updated 2 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆87Updated 2 months ago
- ☆164Updated 6 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆209Updated last year
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆30Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆69Updated last year
- ☆84Updated 3 months ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆84Updated 7 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆87Updated 2 months ago
- Stateful LLM Serving☆95Updated 10 months ago
- Paper-reading notes for Berkeley OS prelim exam.☆14Updated last year
- ☆85Updated 9 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Updated last month
- Preview Code for Continuum Paper☆32Updated last week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆49Updated 11 months ago
- ☆131Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆53Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆52Updated last year
- ☆80Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆110Updated 10 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆151Updated this week
- Accepted to MLSys 2026☆70Updated last week
- ☆20Updated 7 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆101Updated last month
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆58Updated last year
- ☆41Updated 3 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆279Updated this week
- ☆150Updated last year