ashvardanian
Researcher, Founder, & Investor @unum-cloud, @cpp-armenia
Founder @ UnumSan Francisco, London, Yerevan
Pinned Repositories
memchr_vs_stringzilla
memchr vs stringzilla - up to 7x throughput difference between two SIMD-accelerated substring search libraries in Rust
ParallelReductionsBenchmark
Thrust, CUB, TBB, AVX2, CUDA, OpenCL, OpenMP, SyCL - all it takes to sum a lot of numbers fast!
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 📐
StringZilla
Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging NEON, AVX2, AVX-512, and SWAR to accelerate search, sort, edit distances, alignment scores, etc 🦖
SwiftSemanticSearch
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
usearch-molecules
Searching for structural similarities across billions of molecules in milliseconds
ucall
Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️
uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
usearch
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
ustore
Multi-Modal Database replacing MongoDB, Neo4J, and Elastic with 1 faster ACID solution, with NetworkX and Pandas interfaces, and bindings for C 99, C++ 17, Python 3, Java, GoLang 🗄️
ashvardanian's Repositories
ashvardanian/StringZilla
Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging NEON, AVX2, AVX-512, and SWAR to accelerate search, sort, edit distances, alignment scores, etc 🦖
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 📐
ashvardanian/SwiftSemanticSearch
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
ashvardanian/ParallelReductionsBenchmark
Thrust, CUB, TBB, AVX2, CUDA, OpenCL, OpenMP, SyCL - all it takes to sum a lot of numbers fast!
ashvardanian/usearch-molecules
Searching for structural similarities across billions of molecules in milliseconds
ashvardanian/memchr_vs_stringzilla
memchr vs stringzilla - up to 7x throughput difference between two SIMD-accelerated substring search libraries in Rust
ashvardanian/usearch-binary
Binary vector search example using Unum's USearch engine and pre-computed Wikipedia embeddings from Co:here and MixedBread
ashvardanian/tinysemver
Tiny Semantic Versioning (SemVer) library with LLMs and GitHub CI, that doesn't depend on 300K lines of JavaScript code and fits in a single Python file
ashvardanian/cpp-cuda-python-starter-kit
Parallel Computing starter project to build GPU & CPU kernels in CUDA & C++ and call them from Python without a single line of CMake using PyBind11
ashvardanian/MongooseMiner
Documentation retrieval system to help LLMs navigate less-popular (yet often more powerful) Python libraries
ashvardanian/LibSee
Link to this library and it will log all the LibC functions you are calling and how much time you are spending in them!
ashvardanian/affine-gaps
Less-wrong single-file Numba-accelerated Python implementation of Gotoh affine gap penalty extensions for the Needleman–Wunsch, Smith-Waterman, and Levenshtein algorithms for sequence alignment
ashvardanian/TenPack
Fast Tensors Packaging library for text, image, video, and audio data compatible with PyTorch, TensorFlow, & NumPy 🖼️🎵🎥 ➡️ 🧠
ashvardanian/AssemblyStats
A research project highlighting the rarity of SIMD instructions in modern software
ashvardanian/minSH
A minimal Python re-implementation of the A* with seed heuristic for exact global alignmnet (edit distance) in near-linear time
ashvardanian/scaling-democracy
GPU-accelerated Schulze voting method in Python, Numba, and CUDA, using ideas from Algebraic Graph Theory
ashvardanian/HaversineSimSIMD
Staging area for Haversine distance computations in SimSIMD and USearch
ashvardanian/spacev-1b
Billion-scale Semantic Search dataset derived from Microsoft SpaceV for Vector Search benchmarks
ashvardanian/ucall
Remote Procedure Calls - 50x lower latency and 70x higher bandwidth than FastAPI, implementing REST & JSON-RPC over io_uring and SIMDJSON ☎️
ashvardanian/VectorHub
VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.
ashvardanian/usearch
Vector Search engine in a single file - supporting C++ 11, C 99, Python 3, JavaScript, Rust, Java, GoLang, Objective-C, Swift, Wolfram, Docker, and WebAssembly 🔍
ashvardanian/langchain
🦜🔗 Build context-aware reasoning applications
ashvardanian/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
ashvardanian/sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
ashvardanian/uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
ashvardanian/albucore
A high-performance image processing library designed to optimize and extend the Albumentations library with specialized functions for advanced image transformations. Perfect for developers working in computer vision who require efficient and scalable image augmentation.
ashvardanian/ashvardanian
My GitHub page :)
ashvardanian/nltk
NLTK Source
ashvardanian/sse-popcount
SIMD (SSE) population count --- http://0x80.pl/articles/sse-popcount.html
ashvardanian/swift-transformers
Swift Package to implement a transformers-like API in Swift