ashvardanian / SimSIMD
Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, & SVE2 📐
☆1,256Updated this week
Alternatives and similar repositories for SimSIMD:
Users that are interested in SimSIMD are comparing it to the libraries listed below
- Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C…☆2,556Updated 3 weeks ago
- Up to 10x faster strings for C, C++, Python, Rust, Swift & Go, leveraging NEON, AVX2, AVX-512, SVE, & SWAR to accelerate search, hashing,…☆2,425Updated this week
- Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_u…☆1,191Updated last month
- An extensible, state-of-the-art columnar file format☆1,118Updated this week
- Multi-Modal Database replacing MongoDB, Neo4J, and Elastic with 1 faster ACID solution, with NetworkX and Pandas interfaces, and bindings…☆574Updated last year
- Learning how to write "Less Slow" code in C++ 20, C 99, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception hand…☆454Updated this week
- C++ template library for high performance SIMD based sorting algorithms☆919Updated this week
- Lightning fast data version control system for structured and unstructured machine learning datasets. We aim to make versioning datasets …☆914Updated last week
- An efficient C++17 GPU numerical computing library with Python-like syntax☆1,265Updated this week
- Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, v…☆4,227Updated this week
- The Fast Vector Similarity Library is designed to provide efficient computation of various similarity measures between vectors.☆380Updated this week
- RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-a…☆848Updated this week
- Tile primitives for speedy kernels☆2,090Updated this week
- Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library☆1,590Updated 5 months ago
- ☆575Updated 2 months ago
- Making data lake work for time series☆1,153Updated 6 months ago
- nanobind: tiny and efficient C++/Python bindings☆2,618Updated last week
- An easy-to-use and fast library for task-based parallelism, utilizing coroutines.☆320Updated 5 months ago
- 🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of item…☆802Updated 3 months ago
- Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator☆208Updated last year
- Deep learning at the speed of light.☆1,517Updated 2 weeks ago
- Test and benchmark suite for sort implementations.☆376Updated this week
- nsync is a C library that exports various synchronization primitives, such as mutexes☆1,123Updated 7 months ago
- HNSW tutorial☆133Updated last year
- ☆1,022Updated 3 months ago
- Towards a New File Format☆202Updated 3 weeks ago
- cuVS - a library for vector search and clustering on the GPU☆313Updated this week
- Expressive Vector Engine - SIMD in C++ Goes Brrrr☆1,157Updated this week
- Embeddable property graph database management system built for query speed and scalability. Implements Cypher.☆1,742Updated this week
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆2,099Updated last week