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.
☆862Updated 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☆356Updated this week
- RAPIDS Memory Manager☆561Updated last week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆366Updated last month
- ☆530Updated last week
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆155Updated 3 years ago
- common in-memory tensor structure☆968Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,038Updated 11 months ago
- CUDA Kernel Benchmarking Library☆596Updated 2 weeks ago
- CUDA Core Compute Libraries☆1,573Updated this week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆785Updated last month
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,288Updated this week
- An Aspiring Drop-In Replacement for NumPy at Scale☆854Updated 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…☆465Updated 2 weeks ago
- ☆411Updated last year
- CUDA Python: Performance meets Productivity☆1,265Updated this week
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆667Updated last month
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆314Updated this week
- An open-source efficient deep learning framework/compiler, written in python.☆692Updated last month
- Common source, scripts and utilities for creating Triton backends.☆311Updated last week
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆208Updated last year
- The Triton backend for the ONNX Runtime.☆140Updated 2 weeks ago
- High performance model preprocessing library on PyTorch☆650Updated last year
- A library for building and serving multi-node distributed faiss indices.☆264Updated last year
- Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, an…☆1,294Updated last month
- Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.☆597Updated this week
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,737Updated last year
- A tool for bandwidth measurements on NVIDIA GPUs.☆393Updated last month
- Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.☆199Updated 2 months ago
- Some useful tips for faiss☆616Updated last year
- HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of…☆141Updated last week