#Simd

Showing 52 of 52 repositories tagged #simd, ranked by stars

Tencent
Tencent
ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Score
100
โ˜… 23.5k โ‘‚ 4.5k +14/day
C++
RyanCodrai
RyanCodrai
turbovec

A vector index built on TurboQuant, written in Rust with Python bindings

Score
100
โ˜… 12.6k โ‘‚ 1.1k +59/day
Python
bytedance
bytedance
sonic

A blazingly fast JSON serializing & deserializing library

Score
100
โ˜… 9.5k โ‘‚ 456 +19/day
Go
ARM-software
ARM-software
ComputeLibrary

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

Score
50
โ˜… 3.2k โ‘‚ 816 +2/day
C++
hora-search
hora-search
hora

๐Ÿš€ efficient approximate nearest neighbor search algorithm collections library written in Rust ๐Ÿฆ€ .

Score
89
โ˜… 2.7k โ‘‚ 78 โ€”
Rust
google
google
XNNPACK

High-efficiency floating-point neural network inference operators for mobile, server, and Web

Score
100
โ˜… 2.4k โ‘‚ 518 +2/day
C
ermig1979
ermig1979
Simd

C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON, SVE for ARM, HVX for Hexagon

Score
86
โ˜… 2.3k โ‘‚ 452 +1/day
C++
bitshifter
bitshifter
glam-rs

A simple and fast linear algebra library for games and graphics

Score
100
โ˜… 2.0k โ‘‚ 195 +8/day
Rust
ashvardanian
ashvardanian
NumKong

SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types โ€” from 6-bit floats to 64-bit complex โ€” across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go ๐Ÿ“

Score
67
โ˜… 1.8k โ‘‚ 124 โ€”
C
Maratyszcza
Maratyszcza
NNPACK

Acceleration package for neural networks on multi-core CPUs

Score
43
โ˜… 1.7k โ‘‚ 320 โ€”
C
BurntSushi
BurntSushi
memchr

Optimized string search routines for Rust.

Score
95
โ˜… 1.5k โ‘‚ 148 +14/day
Rust
simd-lite
simd-lite
simd-json

Rust port of simdjson

Score
84
โ˜… 1.4k โ‘‚ 101 โ€”
Rust
tjake
tjake
Jlama

Jlama is a modern LLM inference engine for Java

Score
67
โ˜… 1.3k โ‘‚ 159 +1/day
Java
libxsmm
libxsmm
libxsmm

Library for specialized dense and sparse matrix operations, and deep learning primitives.

Score
71
โ˜… 965 โ‘‚ 203 โ€”
C
segmentio
segmentio
asm

Go library providing algorithms optimized to leverage the characteristics of modern CPUs

Score
33
โ˜… 921 โ‘‚ 38 โ€”
Go
cloudwego
cloudwego
sonic-rs

A fast Rust JSON library based on SIMD.

Score
74
โ˜… 900 โ‘‚ 60 +3/day
Rust
mukel
mukel
llama3.java

Llama 3+ inference in pure Java

Score
100
โ˜… 813 โ‘‚ 94 โ€”
Java
TkTech
TkTech
pysimdjson

Python bindings for the simdjson project.

Score
50
โ˜… 767 โ‘‚ 63 โ€”
Python
rust-lang
rust-lang
stdarch

Rust's standard library vendor-specific APIs and run-time feature detection

Score
79
โ˜… 686 โ‘‚ 333 +2/day
Rust
pikkr
pikkr
pikkr

JSON parser which picks up values directly without performing tokenization in Rust

Score
26
โ˜… 641 โ‘‚ 15 โ€”
Rust
rusticstuff
rusticstuff
simdutf8

SIMD-accelerated UTF-8 validation for Rust.

Score
68
โ˜… 601 โ‘‚ 33 โ€”
Rust
Volcomix
Volcomix
virtual-background

Demo on adding virtual background to a live video stream in the browser

Score
0
โ˜… 523 โ‘‚ 128 โ€”
TypeScript
mosra
mosra
corrade

C++11 multiplatform utility library

Score
0
โ˜… 521 โ‘‚ 112 โ€”
C++
Lokathor
Lokathor
wide

A crate to help you go wide. By which I mean use SIMD stuff.

Score
63
โ˜… 517 โ‘‚ 54 +1/day
Rust
facex-engine
facex-engine
facex

Full face stack that runs entirely in the browser. Detection, 576-point 3D mesh, recognition, anti-spoof, smile โ€” all WebAssembly, zero server. Apache 2.0.

Score
57
โ˜… 306 โ‘‚ 45 +1/day
C
smu160
smu160
PhastFT

A high-performance Fast Fourier Transform (FFT) library written in pure and safe Rust.

Score
58
โ˜… 267 โ‘‚ 14 โ€”
Rust
predict-idlab
predict-idlab
tsdownsample

High-performance time series downsampling algorithms for visualization

Score
100
โ˜… 233 โ‘‚ 22 โ€”
Jupyter Notebook
likeslines-maker
likeslines-maker
VectorRAG.Net

VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.

Score
33
โ˜… 171 โ‘‚ 29 โ€”
C#
holypolyfoundation
holypolyfoundation
bs-p

Ultra-low latency AVX-512 Polymarket market-making kernel (Logit Jump-Diffusion + Avellaneda-Stoikov in logit space)

Score
100
โ˜… 157 โ‘‚ 38 โ€”
C
Ameobea
Ameobea
neural-network-from-scratch

A neural network library written from scratch in Rust along with a web-based application for building + training neural networks + visualizing their outputs

Score
0
โ˜… 144 โ‘‚ 13 โ€”
Rust
Frikallo
Frikallo
axiom

High-performance C++ tensor library with NumPy/PyTorch-like API

Score
29
โ˜… 111 โ‘‚ 3 +1/day
C++
nervosnetwork
nervosnetwork
faster-hex

fast hex

Score
47
โ˜… 102 โ‘‚ 20 โ€”
Rust
skerkour
skerkour
chacha20-blake3

The official implementation of the ChaCha20-BLAKE3 AEAD cipher with SIMD acceleration - https://kerkour.com/chacha20-blake3

Score
21
โ˜… 100 โ‘‚ 7 โ€”
Rust
krish567366
krish567366
submicro-execution-engine

Sub-microsecond bare-metal execution engine with deterministic replay, lock-free order path, and hardware-timestamped latency measurement.

Score
67
โ˜… 99 โ‘‚ 17 โ€”
C++
awesomized
awesomized
crc-fast-rust

World's fastest generic CRC calculator for all known CRC-16, CRC-32, and CRC-64 variants, as well as bring-your-own custom parameters, using SIMD intrinsics, which can exceed 100GiB/s on modern systems. Supplies a C/C++ compatible library for use with languages other than Rust.

Score
16
โ˜… 91 โ‘‚ 16 โ€”
Rust
QuState
QuState
spinoza

A high performance Quantum State Simulator implemented in pure Rust

Score
11
โ˜… 91 โ‘‚ 15 โ€”
Rust
SpaceCell
SpaceCell
minarrow

Fast, minimal, and ergonomic zero-copy Apache Arrow tabular data implementation in Rust, with PyO3, Python bindings, shared-memory and low-latency SIMD for data-engineering and columnar workloads. Bridge to Polars and Arrow-rs over FFI effortlessly.

Score
42
โ˜… 90 โ‘‚ 1 โ€”
Rust
bluescarni
bluescarni
heyoka.py

Python library for ODE integration via Taylor's method and LLVM

Score
0
โ˜… 89 โ‘‚ 14 +1/day
Python
gyrdym
gyrdym
ml_linalg

SIMD-based linear algebra and statistics for data science with dart

Score
14
โ˜… 88 โ‘‚ 10 โ€”
Dart
awxkee
awxkee
libblur

High performance blur in pure Rust

Score
37
โ˜… 86 โ‘‚ 6 โ€”
Rust
fwessels
fwessels
go-cv

Computer Vision package in pure Go taking advantage of SIMD acceleration

Score
0
โ˜… 86 โ‘‚ 6 โ€”
Go
santhsecurity
santhsecurity
keyhog

Open-source secret scanner in Rust. Service-specific detectors, SIMD on the CPU and an optional GPU path, live verification of which leaked keys are still active, and SARIF output.

Score
53
โ˜… 84 โ‘‚ 13 โ€”
Rust
velvia
velvia
compressed-vec

SIMD Floating point and integer compressed vector library

Score
5
โ˜… 80 โ‘‚ 9 โ€”
Rust
cyberlife-coder
cyberlife-coder
VelesDB

The local-first memory engine for AI agents. One offline Rust binary fuses vector + graph + columnar under SQL โ€” remember / recall / why over the Model Context Protocol. why() reconnects a decision to its context across sessions, where pure vector recall (Mem0/Zep) goes blind. Runs on server, laptop, browser, edge. Zero cloud.

Score
0
โ˜… 75 โ‘‚ 8 +1/day
Rust
StratCraftsAI
StratCraftsAI
NexusFix

A zero-alloc, compile-time hardened FIX engine built for sub-100ns execution.

Score
33
โ˜… 71 โ‘‚ 13 +5/day
C++
jvdd
jvdd
argminmax

Efficient argmin & argmax

Score
32
โ˜… 64 โ‘‚ 10 โ€”
Rust
djugei
djugei
optimath

A #[no_std] LinAlg library

Score
0
โ˜… 52 โ‘‚ 2 โ€”
Rust
MPCoreDeveloper
MPCoreDeveloper
SharpCoreDB

High-Performance Encrypted Database for .NET 10 | Embedded + gRPC Server | Vector Search โ€ข GraphRAG โ€ข Analytics

Score
67
โ˜… 35 โ‘‚ 5 โ€”
C#
maxgfr
maxgfr
brutifi

High-performance WiFi security testing app in Rust for educational and authorized security audits.

Score
0
โ˜… 35 โ‘‚ 2 โ€”
Rust
anwitars
anwitars
grab

High-performance, declarative stream processor for delimited text data.

Score
0
โ˜… 21 โ‘‚ 0 โ€”
Rust
VectorAlpha-dev
VectorAlpha-dev
VectorTA

High-performance technical analysis library in Rust with 340+ indicators, SIMD/CUDA acceleration, and optional Python/WASM bindings.

Score
0
โ˜… 20 โ‘‚ 10 โ€”
Rust
AndreaBozzo
AndreaBozzo
dataprof

Rust profiling library with PyO3 bindings

Score
33
โ˜… 16 โ‘‚ 1 โ€”
Rust
Related Topics
#rust#avx512#neural-network#neon#json#machine-learning#wasm#python#high-performance#avx2#rag#vector-search

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly