Berkeley-Large-RAG / RAG-DS-ServeLinks
DS SERVE: The Largest Open Vector Store over Pretain Data; A Framework for Efficient and Scalable Neural Retrieval
☆37Updated last month
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☆136Updated last year
- Easy, Fast, and Scalable Multimodal AI☆92Updated this week
- ☆27Updated 9 months ago
- Memory-Bounded GPU Acceleration for Vector Search☆32Updated 2 weeks ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆113Updated 2 weeks ago
- Modular and structured prompt caching for low-latency LLM inference☆110Updated last year
- Implementation of the paper "Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search" by Severo et al.☆87Updated 11 months ago
- ☆63Updated 8 months ago
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆485Updated last month
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- AI-Driven Research Systems (ADRS)☆113Updated last month
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆245Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆79Updated 2 weeks ago
- Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainings☆114Updated 5 months ago
- ☆48Updated last year
- Bamboo-7B Large Language Model☆93Updated last year
- A fast header-only graph-based index for approximate nearest neighbor search (ANNS). https://flatnav.net☆39Updated last week
- ☆47Updated 8 months ago
- ☆92Updated last year
- KV cache compression for high-throughput LLM inference☆148Updated 11 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆217Updated 7 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆255Updated last year
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆389Updated last week
- Code repository for the paper - "AdANNS: A Framework for Adaptive Semantic Search"☆66Updated 2 years ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆31Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆176Updated 8 months ago
- ☆36Updated 11 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆30Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year