Berkeley-Large-RAG / RAG-DS-ServeLinks
DS SERVE: The Largest Open Vector Store over Pretain Data; A Framework for Efficient and Scalable Neural Retrieval
☆29Updated 2 weeks ago
Alternatives and similar repositories for RAG-DS-Serve
Users that are interested in RAG-DS-Serve are comparing it to the libraries listed below
Sorting:
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- Easy, Fast, and Scalable Multimodal AI☆81Updated this week
- ☆63Updated 7 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆244Updated last year
- Modular and structured prompt caching for low-latency LLM inference☆105Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆106Updated 3 months ago
- KV cache compression for high-throughput LLM inference☆148Updated 10 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆55Updated this week
- ☆48Updated last year
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- Bamboo-7B Large Language Model☆93Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆215Updated 6 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- Memory-Bounded GPU Acceleration for Vector Search☆32Updated 2 months ago
- AI-Driven Research Systems (ADRS)☆103Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- Code repository for the paper - "AdANNS: A Framework for Adaptive Semantic Search"☆65Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 9 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆261Updated last week
- Memory optimized Mixture of Experts☆72Updated 5 months ago
- ☆27Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆249Updated last year
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆29Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆203Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Updated 5 months ago
- ☆34Updated 10 months ago
- LM engine is a library for pretraining/finetuning LLMs☆102Updated this week