Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX Video Super Resolution VSR, SRMD, RealSR, Anime4K, RIFE, IFRNet, CAIN, DAIN, and ACNet.
- waifu2x
- anime4k
- super-resolution
- video-enlarger
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
- mnn
- convolution
- vulkan
- embedded-devices
Avatars for Zoom, Skype and other video-conferencing apps.
Nano vLLM
:fire: An extremely fast, React-like JavaScript library for building modern user interfaces
- inferno
- vdom
- performance
- react
Machine learning, in numpy
A static analyzer for Java, C, C++, and Objective-C
🎨 The exhaustive Pattern Matching library for TypeScript, with smart type inference.
- pattern-matching
- typescript
- ts
- pattern
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Instant messaging platform. Backend in Go. Clients: Swift iOS, Java Android, JS webapp, scriptable command line; chatbots
- chat
- chat-application
- chatapp
- go
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
Translated✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field (冰霜之地, "Land of Frost"): notes on source code analysis, system design, and engineering practice
- ios
- objective-c
- swift
- javascript
🎉 performant confetti animation in the browser
- canvas
- confetti
- jsdelivr
- animation
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, K8s, AI inference, and IAM services.
- cloud
- portable
- bare-metal
- hosting
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
- figures
- python
- icml
- nature-machine-intelligence
Translated🔥 🎉newbee-mall is an e-commerce system that includes a basic version (Spring Boot+Thymeleaf), a version with separated front end and back end (Spring Boot+Vue 3+Element-Plus+Vue-Router 4+Pinia+Vant 4), a flash sale version, a Go language version, and a microservices version (Spring Cloud Alibaba+Nacos+Sentinel+Seata+Spring Cloud Gateway+OpenFeign+ELK). The front-end mall system includes modules such as the home page portal, product categories, new arrivals, home page carousel, product recommendations, product search, product display, shopping cart, order checkout, order process, personal order management, member center, and help center. The back-end management system includes modules such as the data dashboard, carousel image management, product management, order management, member management, category management, and settings.
vCluster creates tenant clusters: fully isolated environments delivered as managed Kubernetes, or as the foundation for Slurm, Ray, Run:ai and inference clusters. Each gets its own API server, CRDs and RBAC, and runs on an existing cluster or standalone on bare metal. CNCF Certified Kubernetes.
- kubernetes
- vcluster
- virtual-clusters
- multi-tenancy
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
The Triton Inference Server provides an optimized cloud and edge inferencing solution.