9 results found Sort:

Tencent
ncnn Tencent
4.2k
20.5k
other
572
ncnn is a high-performance neural network inference framework optimized for the mobile platform
ios mlir ncnn onnx simd caffe keras mxnet riscv vulkan android darknet pytorch arm-neon inference tensorflow deep-learning neural-network high-preformance artificial-intelligence
Created 2017-06-30
3,329 commits to master branch, last one 7 days ago
Tencent
FeatherCNN Tencent
284
1.2k
unknown
100
FeatherCNN is a high performance inference engine for convolutional neural networks.
ios caffe android arm-neon inference-engine convolutional-neural-networks
Created 2018-04-27
19 commits to master branch, last one 5 years ago
ashvardanian
SimSIMD ashvardanian
59
985
apache-2.0
18
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, & S...
avx2 blas neon simd numpy scipy avx512 arm-sve float16 metrics arm-neon assembly bfloat16 vector-search blas-libraries simd-instructions similarity-search similarity-measures distance-calculation information-retrieval
Created 2023-03-14
1,127 commits to main branch, last one 20 hours ago
WojciechMula
sse-popcount WojciechMula
48
326
bsd-2-clause
32
SIMD (SSE) population count --- http://0x80.pl/articles/sse-popcount.html
sse avx2 avx512 aarch64 arm-neon popcount
Created 2015-04-04
141 commits to master branch, last one 7 months ago
spnda
fastgltf spnda
47
312
mit
6
A modern C++17 glTF 2.0 library focused on speed, correctness, and usability
avx cpp sse gltf json neon simd cpp17 cpp20 gltf2 khronos arm-neon cpp-library cpp-modules gltf-loader gltf2-loader cpp17-library cpp20-modules serialization arm-neon-libraries
Created 2022-09-11
517 commits to main branch, last one 4 days ago
AI-performance
embedded-ai.bench AI-performance
29
203
other
14
benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN / TensorFlow Lite etc.
arm ios mnn tnn ncnn android arm-neon benchmark inference embedded-ai tensorflow-lite artificial-intelligence deep-learning-framework deep-learning-inference
This repository has been archived (exclude archived)
Created 2020-06-15
272 commits to master branch, last one 3 years ago
cdl-saarland
rv cdl-saarland
15
105
other
17
RV: A Unified Region Vectorizer for LLVM
avx2 llvm simd spmd avx512 openmp arm-neon compiler outer-loops vectorization loop-optimization function-vectorizer compiler-optimization
Created 2016-11-09
2,068 commits to release/18.x branch, last one about a month ago
xxxxyu
FlexNN xxxxyu
4
40
other
2
Code for ACM MobiCom 2024 paper "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices"
cnn dnn ncnn mobile android arm-neon inference neural-network
Created 2024-10-13
4 commits to main branch, last one about a month ago
wx257osn2
qoixx wx257osn2
5
35
mit
4
Single Header Quite Fast QOI(Quite OK Image Format) Implementation written in C++20
qoi sve avx2 neon simd cpp20 arm-sve arm-neon cpp20-library image-compression lossless-image-compression
Created 2022-02-20
119 commits to master branch, last one 7 months ago