google/XNNPACK
A Google library providing highly optimized neural network inference operators for ARM, x86, WebAssembly, and RISC-V platforms.
Not currently ranked — collecting fresh signals.
star history
XNNPACK provides low-level performance primitives for neural network inference, implementing operators like convolution, pooling, activation functions, and quantization. It targets mobile, server, and web platforms, serving as a backend acceleration layer for high-level ML frameworks including TensorFlow Lite, PyTorch, ONNX Runtime, and MediaPipe. The library supports SIMD optimizations across multiple architectures and includes fixed-point quantization for efficient deployment.
Frequently asked
- What is google/XNNPACK?
- A Google library providing highly optimized neural network inference operators for ARM, x86, WebAssembly, and RISC-V platforms.
- Is XNNPACK open source?
- Yes — google/XNNPACK is an open-source project tracked on heatdrop.
- What language is XNNPACK written in?
- google/XNNPACK is primarily written in C.
- How popular is XNNPACK?
- google/XNNPACK has 2.4k stars on GitHub.
- Where can I find XNNPACK?
- google/XNNPACK is on GitHub at https://github.com/google/XNNPACK.