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.
☆777Updated this week
Related projects ⓘ
Alternatives and complementary repositories for raft
- cuVS - a library for vector search and clustering on the GPU☆224Updated this week
- RAPIDS Memory Manager☆492Updated this week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆356Updated this week
- common in-memory tensor structure☆912Updated last month
- ☆486Updated this week
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆142Updated 3 years ago
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆207Updated last year
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,011Updated 7 months ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,210Updated this week
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,140Updated this week
- GGNN: State of the Art Graph-based GPU Nearest Neighbor Search☆142Updated 3 years ago
- CUDA Core Compute Libraries☆1,278Updated 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…☆433Updated last week
- High performance model preprocessing library on PyTorch☆649Updated 7 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆652Updated last week
- ☆126Updated 2 weeks ago
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆188Updated 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 this week
- Pipeline Parallelism for PyTorch☆726Updated 2 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,979Updated this week
- Graph Library for Approximate Similarity Search☆91Updated 6 months ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆306Updated last week
- FlashInfer: Kernel Library for LLM Serving☆1,452Updated this week
- CUDA Kernel Benchmarking Library☆519Updated this week
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆558Updated 3 weeks ago
- A library to analyze PyTorch traces.☆307Updated this week
- The Foundation for All Legate Libraries☆193Updated this week
- CUDA Python Low-level Bindings☆965Updated this week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆270Updated this week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆734Updated this week