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.
☆858Updated 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☆331Updated this week
- RAPIDS Memory Manager☆557Updated this week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆366Updated last month
- ☆524Updated last week
- common in-memory tensor structure☆963Updated last week
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆155Updated 3 years ago
- CUDA Kernel Benchmarking Library☆593Updated last week
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆209Updated last year
- An open-source efficient deep learning framework/compiler, written in python.☆690Updated 3 weeks ago
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,271Updated this week
- CUDA Core Compute Libraries☆1,539Updated 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…☆462Updated last week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆781Updated last month
- CUDA Python: Performance meets Productivity☆1,212Updated this week
- KvikIO - High Performance File IO☆195Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,037Updated 11 months ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆358Updated last week
- ☆146Updated this week
- TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and sup…☆354Updated this week
- High performance model preprocessing library on PyTorch☆650Updated 11 months ago
- Pipeline Parallelism for PyTorch☆757Updated 7 months ago
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆657Updated last month
- NVIDIA Math Libraries for the Python Ecosystem☆248Updated last week
- Common source, scripts and utilities for creating Triton backends.☆310Updated this week
- A library to analyze PyTorch traces.☆348Updated last week
- An efficient C++17 GPU numerical computing library with Python-like syntax☆1,296Updated this week
- Graph Library for Approximate Similarity Search☆107Updated 10 months ago
- The Triton backend for the ONNX Runtime.☆140Updated last week
- The core library and APIs implementing the Triton Inference Server.☆122Updated last week
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆325Updated this week