Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/XNNPACK
Library/XNNPACKForked

google/XNNPACK

XNNPACK

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

View on GitHub↗Upstream google/XNNPACK↗

Builder

Google

Google

google • big-tech

Stars

2,349

Using upstream star count

Forks

495

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Sep 13, 2019

Project creation date

README Summary

XNNPACK is a highly optimized solution for neural network inference on ARM, x86, WebAssembly, and RISC-V platforms. XNNPACK is not intended for direct use by deep learning practitioners and researchers; instead it provides low-level performance primitives for accelerating high-level machine learning frameworks, such as [TensorFlow Lite](https://www.tensorflow.org/lite), [TensorFlow.js](https://www.tensorflow.org/js), [PyTorch](https://pytorch.org/), [ONNX Runtime](https://onnxruntime.ai), [Execu

Community Evaluation

Loading…

AI Dev Skills

Unmapped

ARM NEON OptimizationCross-platform Performance EngineeringHardware AccelerationLow-level Neural Network OperatorsMobile AI InferenceNeural Network OptimizationQuantized Neural NetworksSIMD ProgrammingWebAssembly SIMDx86 AVX Optimization

Tags

ARM NEON OptimizationCross-platform Performance EngineeringHardware AccelerationLow-level Neural Network OperatorsMobile AI InferenceNeural Network OptimizationQuantized Neural NetworksSIMD ProgrammingWebAssembly SIMDx86 AVX OptimizationBenchmarkingDeep LearningEvalsForkedMachine LearningMobileModel OptimizationONNXPythonPyTorchQuantizationResearch / PapersSimulationTensorFlow

Taxonomy

AI Trends

On-device AIEdge ComputingMobile AIQuantized Neural Networks

category

Model TrainingFoundation ModelsEvals & BenchmarkingInference & ServingRoboticsLearning ResourcesIndustry: Gaming

Deployment Context

Edge/MobileBrowser/WASMCloud APISelf-hostedOn-premise

Modalities

Multimodal

Skill Areas

Neural Network OptimizationHardware AccelerationMobile AI InferenceSIMD ProgrammingCross-platform Performance EngineeringLow-level Neural Network OperatorsQuantized Neural NetworksARM NEON Optimizationx86 AVX OptimizationWebAssembly SIMD

tag

BenchmarkingDeep LearningEvalsForkedMachine LearningMobileModel OptimizationONNXPyTorchPythonQuantizationResearch / PapersSimulationTensorFlow

Use Cases

Mobile Neural Network InferenceEdge AI DeploymentBrowser-based ML ModelsServer-side Model ServingReal-time AI ApplicationsEmbedded AI Systems

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

20

Merge pull request #9642 from ken-unger:qemu-riscv64

XNNPACK Team • Mar 13, 2026

2077bf8

Add simd::convert for s32 <-> f32 conversions

Volodymyr Kysenko • Mar 12, 2026

3d17a5c

Use generic bit_cast.

Volodymyr Kysenko • Mar 12, 2026

a7e5a2a

Quality

production
Quality
high
Maturity
production

Categories

Evals & BenchmarkingPrimaryInference & ServingLearning ResourcesIndustry: GamingFoundation ModelsModel TrainingRoboticsEdge & Mobile AISearch & KnowledgeOther AI / ML

PM Skills

Cost & EfficiencyData & Evaluation

Languages

C100.0%

Timeline

Project created
Sep 13, 2019
Forked
Mar 13, 2026
Your last push
2 months ago
Upstream last push
16 days ago
Tracked since
Mar 13, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…