#
Starred repositories
A curated list of awesome Qt and QML libraries, resources, projects, and shiny things.
A retargetable MLIR-based machine learning compiler and runtime toolkit.
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
Zero Bubble Pipeline Parallelism
LightSeq: A High Performance Library for Sequence Processing and Generation
Transformer related optimization, including BERT, GPT
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Serverless LLM Serving for Everyone.
✨✨✨ Geeker Admin，基于 Vue3.4、TypeScript、Vite5、Pinia、Element-Plus 开源的一套后台管理框架。
An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation
⚡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and …
A code generator for array-based code on CPUs and GPUs
how to learn PyTorch and OneFlow
how to optimize some algorithm in cuda.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Universal LLM Deployment Engine with ML Compilation
BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
Open deep learning compiler stack for cpu, gpu and specialized accelerators
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Official inference library for Mistral models