Simplify your onnx model

Unofficial Python system monitor and library for small IPS USB-C displays like Turing Smart Screen or XuanFang

Tensors and Dynamic neural networks in Python with strong GPU acceleration

ONNX Optimizer

Open Neural Network Exchange

nanobind: tiny and efficient C++/Python bindings

Public repository of the Micro QuickJS Javascript Engine

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

the python api for axengine runtime

Try Kernel

PicoRuby shell for Raspberry Pi Pico (RP2040)

common in-memory tensor structure

PicoRuby is the smallest Ruby implementation for one-chip microcontrollers

A Raspberry Pi Pico Emulator in JavaScript

Helm 3 charts to deploy a Supabase on Kubernetes

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

novel game engine for Browser, iOS, Android , etc

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

A transpiler that converts Python code to LLVM IR and compiles it to machine code.