rapidsai / raft
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
☆870Updated this week
Alternatives and similar repositories for raft:
Users that are interested in raft are comparing it to the libraries listed below
- cuVS - a library for vector search and clustering on the GPU☆382Updated this week
- RAPIDS Memory Manager☆572Updated last week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆373Updated last week
- ☆537Updated this week
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆208Updated last year
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆156Updated 4 years ago
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,315Updated last week
- CUDA Kernel Benchmarking Library☆621Updated this week
- common in-memory tensor structure☆982Updated 2 weeks ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,040Updated last year
- An open-source efficient deep learning framework/compiler, written in python.☆698Updated 2 months ago
- CUDA Core Compute Libraries☆1,610Updated this week
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆472Updated 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…☆140Updated this week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,303Updated this week
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆689Updated 2 months ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆376Updated 2 weeks ago
- A throughput-oriented high-performance serving framework for LLMs☆797Updated 7 months ago
- Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, an…☆1,343Updated 3 weeks ago
- Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.☆219Updated this week
- ☆151Updated this week
- A library to analyze PyTorch traces.☆366Updated this week
- Graph Library for Approximate Similarity Search☆113Updated 11 months ago
- KvikIO - High Performance File IO☆206Updated this week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆786Updated 2 months ago
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆318Updated this week
- GGNN: State of the Art Graph-based GPU Nearest Neighbor Search☆154Updated 2 months ago
- HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training☆992Updated last month
- High performance model preprocessing library on PyTorch☆650Updated last year
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,745Updated last year