multi-gpu

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

Multi-threaded GUI manager for mass creation of AI-generated art with support for multiple GPUs.

GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

Chains stable-diffusion-webui instances together to facilitate faster image generation.

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

The most feature-complete local AI workstation. Multi-GPU inference, integrated Stable Diffusion + ADetailer, voice cloning, research-grade ELO testing, and tool-calling code editor. 100% local. Zero subscriptions. Your GPUs deserve better.

:dart: Gradient Accumulation for TensorFlow 2

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualification, CUDA weight sharing, and multi-GPU planning.

AI hardware fit calculator for LLM, embedding, reranker, OCR and VLM workloads — VRAM, throughput, licensing and multi-GPU planning