google/XNNPACK
XNNPACK
High-efficiency floating-point neural network inference operators for mobile, server, and Web
Builder
google • big-tech
Stars
2,291
Using upstream star count
Forks
475
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 library of floating-point neural network inference operators designed for mobile, server, and web platforms. It provides efficient implementations of common neural network operations with extensive hardware acceleration support across different architectures including ARM, x86, and WebAssembly.
AI Dev Skills
Unmapped
Neural Network OptimizationHardware AccelerationMobile AI InferenceSIMD ProgrammingCross-platform Performance EngineeringLow-level Neural Network OperatorsQuantized Neural NetworksARM NEON Optimizationx86 AVX OptimizationWebAssembly SIMD
Tags
Neural Network OptimizationHardware AccelerationMobile AI InferenceSIMD ProgrammingCross-platform Performance EngineeringLow-level Neural Network OperatorsQuantized Neural NetworksARM NEON Optimizationx86 AVX OptimizationWebAssembly SIMDEdge/MobileEdge AI DeploymentSelf-hostedReal-time AI ApplicationsMultimodalOn-premiseOn-device AIBrowser/WASMMobile Neural Network InferenceMobile AICloud APIBrowser-based ML ModelsServer-side Model ServingEmbedded AI SystemsEdge ComputingC
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 1 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
production- Quality
- high
- Maturity
- production
Categories
Dev Tools & AutomationPrimaryInference & ServingML Platform & InfrastructureCoding & Dev ToolsMultimodal AIEdge & Mobile AIOther AI / MLRoboticsFoundation Models
PM Skills
Developer Platform
Languages
C100.0%
Timeline
- Project created
- Sep 13, 2019
- Forked
- Mar 13, 2026
- Your last push
- 1 months ago
- Upstream last push
- 6 days ago
- Tracked since
- Mar 13, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…