microsoft / RetrievalAttentionLinks
Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.
☆52Updated 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☆55Updated last week
- Stateful LLM Serving☆73Updated 3 months ago
- ☆103Updated 7 months ago
- ☆62Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆163Updated 9 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ☆54Updated last year
- ☆121Updated 5 months ago
- ☆77Updated 2 months ago
- Modular and structured prompt caching for low-latency LLM inference☆96Updated 7 months ago
- ☆109Updated 8 months ago
- ☆60Updated last month
- 16-fold memory access reduction with nearly no loss☆99Updated 2 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆21Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated 2 weeks ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆54Updated last week
- A lightweight design for computation-communication overlap.☆143Updated this week
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- ☆74Updated 4 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- ☆32Updated last year
- DeeperGEMM: crazy optimized version☆69Updated last month
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆39Updated last week
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆26Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆113Updated this week
- ☆84Updated 3 years ago
- A minimal implementation of vllm.☆43Updated 10 months ago
- ☆67Updated 8 months ago