gpu

🪶 Lightweight OpenAI drop-in replacement for Kubernetes

The Best TypeScript framework for fine-tuning

PyTorch tutorials A to Z

AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs.

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

Live AI-powered screen translation via LLMs & GPU OCR. 26 languages, manga support, PDF/CBZ conversion, audio reading, cloud or fully local operation. For gamers, manga readers, and language learners.

One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

Self-host a ChatGPT-style web interface for Ollama 🦙

Extensible generative AI platform on Kubernetes with OpenAI-compatible APIs.

Hand-written NVFP4 W4A16 CUDA kernels for Volta

Self-hosted AI-powered transcription platform with speaker diarization, search, and collaboration features. Built with Svelte, FastAPI, and Docker for easy deployment.

Neural networks library for machine learning on PHP

AMD ROCm Installation Guide on RX 6600 XT + TensorFlow and PyTorch

Stable Diffusion WebUI Forge docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

🚀 100% local RAG system with one-command setup. Your data never leaves your server. Apache-2.0

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cloning, and 23 languages.

:dart: Gradient Accumulation for TensorFlow 2

A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.