ashvardanian / SimSIMD
Up to 200x Faster Dot Products & Similarity Metrics β 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 π
β983Updated this week
Related projects β
Alternatives and complementary repositories for SimSIMD
- Fast Open-Source Search & Clustering engine Γ for Vectors & π Strings Γ in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, Cβ¦β2,264Updated this week
- Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uβ¦β1,141Updated last month
- Multi-Modal Database replacing MongoDB, Neo4J, and Elastic with 1 faster ACID solution, with NetworkX and Pandas interfaces, and bindingsβ¦β549Updated last year
- Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging NEON, AVX2, AVX-512, and SWAR to accelerate search, sort, edit dβ¦β2,233Updated last week
- cuVS - a library for vector search and clustering on the GPUβ224Updated this week
- C++ template library for high performance SIMD based sorting algorithmsβ887Updated last week
- The Fast Vector Similarity Library is designed to provide efficient computation of various similarity measures between vectors.β350Updated 2 months ago
- Lightning fast data version control system for structured and unstructured machine learning datasets. We aim to make versioning datasets β¦β882Updated 3 weeks ago
- An extensible, state-of-the-art columnar file formatβ987Updated this week
- An efficient C++17 GPU numerical computing library with Python-like syntaxβ1,220Updated this week
- β1,003Updated 3 weeks ago
- RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-aβ¦β777Updated this week
- Fast, SQL powered, in-process vector search for any language with an SQLite driverβ268Updated 2 weeks ago
- β234Updated 8 months ago
- Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extensβ¦β1,176Updated this week
- Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera acceleratorβ207Updated 11 months ago
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). β¦β2,001Updated this week
- β571Updated last month
- New file format for storage of large columnar datasets.β453Updated last week
- Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Searchβ1,140Updated this week
- Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)β558Updated last year
- Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vβ¦β3,964Updated this week
- β162Updated 5 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programsβ204Updated 2 months ago
- Stateful load balancer custom-tailored for llama.cppβ563Updated this week
- B-field implementation in Rustβ204Updated 5 months ago
- HNSW tutorialβ113Updated 9 months ago
- An easy-to-use and fast library for task-based parallelism, utilizing coroutines.β307Updated 2 months ago
- A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many differentβ¦β270Updated 3 weeks ago
- Fast Static Symbol Table (FSST): efficient random-access string compressionβ391Updated 3 months ago