SystemPanic/vllm-windows
A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)
A high-throughput and memory-efficient inference and serving engine for LLMs (Windows build & kernels)
FlashInfer: Kernel Library for LLM Serving (Windows build & kernels)
Optimized primitives for collective multi-GPU communication
Pynini for Windows
OpenFst for Windows
QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
DeepGEMM: clean and efficient BLAS kernel library on GPU (Windows build & kernels)
Fast C++ logging library.
CUDA Templates for Linear Algebra Subroutines
High-performance safetensors model loader
Session store using redis-sessions for Connect
🍃 GridFS storage engine for Multer to store uploaded files directly to MongoDb
TVM FFI
Fast, Flexible and Portable Structured Generation
A fast inference library for running LLMs locally on modern consumer-class GPUs
Javascript library for running real-time AI Upscaling in the browser
Simple, unobtrusive authentication for Node.js.
Mediapipe Face Detection (legacy 0.4.1646425229) with Web Worker support
FaceAPI: AI-powered Face Detection & Rotation Tracking, Face Description & Recognition, Age & Gender & Emotion Prediction for Browser and NodeJS using TensorFlow/JS
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Client-side in-memory mongodb backed by localstorage with server sync over http
Display PDFs in your React app as easily as if they were images.
node.js module for Sendy API
CLI to a Gecko desktop app runtime