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.
☆766Updated this week
Related projects ⓘ
Alternatives and complementary repositories for raft
- cuVS - a library for vector search and clustering on the GPU☆210Updated this week
- ☆485Updated this week
- RAPIDS Memory Manager☆492Updated this week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆352Updated last week
- An open-source efficient deep learning framework/compiler, written in python.☆649Updated this week
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,128Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,936Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,010Updated 6 months ago
- CUDA Core Compute Libraries☆1,252Updated this week
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆206Updated last year
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆140Updated 3 years ago
- common in-memory tensor structure☆905Updated last month
- High performance model preprocessing library on PyTorch☆648Updated 7 months ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆301Updated this week
- Graph Library for Approximate Similarity Search☆89Updated 5 months ago
- CUDA Kernel Benchmarking Library☆513Updated 2 weeks ago
- Pipeline Parallelism for PyTorch☆725Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,395Updated this week
- NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale da…☆1,047Updated 2 months ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,202Updated this week
- The Foundation for All Legate Libraries☆189Updated last month
- A library for building and serving multi-node distributed faiss indices.☆252Updated last year
- TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillati…☆534Updated 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…☆426Updated this week
- TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and sup…☆332Updated 2 weeks ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆739Updated this week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆268Updated this week
- A library to analyze PyTorch traces.☆297Updated this week
- ☆411Updated 11 months ago
- This repository contains tutorials and examples for Triton Inference Server☆558Updated this week