rapidsai / cuvsLinks
cuVS - a library for vector search and clustering on the GPU
☆519Updated last week
Alternatives and similar repositories for cuvs
Users that are interested in cuvs are comparing it to the libraries listed below
Sorting:
- RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-a…☆933Updated this week
- RAPIDS Memory Manager☆619Updated this week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆395Updated last month
- ☆185Updated this week
- KvikIO - High Performance File IO☆224Updated last week
- Graph Library for Approximate Similarity Search☆131Updated 2 weeks ago
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆165Updated 4 years ago
- NVIDIA Inference Xfer Library (NIXL)☆633Updated this week
- A library of algorithms for approximate nearest neighbor search in high dimensions, along with a set of useful tools for designing such a…☆161Updated last week
- Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.☆278Updated last week
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,486Updated this week
- ☆75Updated 8 months ago
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆216Updated 2 years ago
- Perplexity GPU Kernels☆469Updated last week
- ☆585Updated last week
- WholeGraph - large scale Graph Neural Networks☆104Updated 10 months ago
- TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and sup…☆391Updated this week
- ☆70Updated 7 months ago
- ☆107Updated 2 weeks ago
- CUDA Kernel Benchmarking Library☆724Updated last week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆353Updated last week
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆451Updated last week
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)☆404Updated last week
- JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs wel…☆377Updated 3 months ago
- A throughput-oriented high-performance serving framework for LLMs☆891Updated last week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆417Updated this week
- kernels, of the mega variety☆502Updated this week
- The Triton backend for the ONNX Runtime.☆162Updated 2 weeks ago
- MSVBASE is a system that efficiently supports complex queries of both approximate similarity search and relational operators. It integrat…☆98Updated 10 months ago
- A library to analyze PyTorch traces.☆412Updated 2 weeks ago