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.
☆884Updated this week
Alternatives and similar repositories for raft
Users that are interested in raft are comparing it to the libraries listed below
Sorting:
- cuVS - a library for vector search and clustering on the GPU☆407Updated this week
- ☆537Updated this week
- RAPIDS Memory Manager☆584Updated this week
- Framework for evaluating ANNS algorithms on billion scale datasets.☆376Updated last week
- CUDA Kernel Benchmarking Library☆644Updated last week
- CUDA Core Compute Libraries☆1,642Updated this week
- Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.☆209Updated last year
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆788Updated 3 months ago
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,044Updated last year
- common in-memory tensor structure☆986Updated last week
- CUDA implementation of Hierarchical Navigable Small World Graph algorithm☆158Updated 4 years ago
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆325Updated this week
- Examples demonstrating available options to program multiple GPUs in a single node or a cluster☆704Updated 3 months ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,324Updated this week
- Pipeline Parallelism for PyTorch☆763Updated 9 months ago
- A library to analyze PyTorch traces.☆372Updated 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…☆476Updated last month
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆383Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆808Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,424Updated this week
- [ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl☆1,744Updated last year
- ☆161Updated this week
- Tile primitives for speedy kernels☆2,352Updated this week
- A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.☆814Updated last week
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search☆1,349Updated last week
- An open-source efficient deep learning framework/compiler, written in python.☆696Updated last week
- Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.☆622Updated last week
- nvidia-modelopt is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculat…☆934Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,059Updated last year
- GGNN: State of the Art Graph-based GPU Nearest Neighbor Search☆156Updated 3 months ago