Sign in

Repository Index

132,241 visible repositories in the index

Tags: Programming languages and compilers
Tags

A repository shows when it has any selected Tag.

Clear Tags
Filters

Filters

Clear all filters

1–20 of 20 · Most stars

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

nidium is an ongoing effort for a mobile hw-accelerated rendering engine to create apps and games. Embedding Mozilla JavaScript VM, Google Skia, Facebook Yoga. https://twitter.com/nidiumproject for updates

  • spidermonkey
  • rendering
  • layout-engine
  • javascript

An Axum-based Rust web framework with Lean 4-verifiable application kernels that run on servers, bare-metal embedded devices, and GPUs, plus integrated security testing.

  • ai-safety
  • ai-security
  • web-security
  • hacking

Zero-copy PDF text extraction library written in Zig. High-performance, memory-mapped parsing with SIMD acceleration.

CicadaPlayer is the player core of AliPlayer, which supports multiple platforms Android, iOS, macOS, Windows, Linux, and WebAssembly for now. The goal is to provide a player core which supports multi-platform, hardware accelerator, and customizable and extensible features. Which supports WideVine drm, LL-HLS, MPEG-DASH and HDR playback.

PypelineC: A hardware description language (HDL) adding high level synthesis(HLS)-like automatic pipelining as a language construct/compiler feature.

  • fpga
  • hardware-description-language
  • vhdl
  • pipelines

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

Parser for GPMF™ formatted telemetry data used within GoPro® cameras.

  • gopro-camera
  • gopro
  • sensor-data
  • mp4-video

A high-performance engine for matrix math, physics simulation, and MCAD and ECAD as code. RunMat checks types, sizes and units before anything runs, executes on CPU and GPU, and runs existing MATLAB-language code as written.

Open source compiler for your whole ML repo (support python, CUDA C/C++) into sass and cuda binary (which are closed sourced by Nvidia); 3-40% faster than Openai Triton for Neural Network (primarily LLM) based training/inferencing

  • compiler
  • compiler-backend
  • compiler-optimization
  • gpu-acceleration