Skip to content

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

1.3 KB
Raw Blame
# ============================================================================
# NVIDIA GPU OVERRIDE (Adds GPU acceleration to base docker-compose.yml)
# ============================================================================
# This override file adds NVIDIA GPU support to the CPU-only base configuration.
#
# Prerequisites:
#   - NVIDIA GPU (Linux only)
#   - nvidia-container-toolkit installed
#   - See README.md for installation instructions
#
# Usage:
#   docker compose -f docker-compose.yml -f docker-compose.gpu.override.yml up -d
#
# Quick start with curl:
#   curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.yml
#   curl -O https://raw.githubusercontent.com/LearningCircuit/local-deep-research/main/docker-compose.gpu.override.yml
#   docker compose -f docker-compose.yml -f docker-compose.gpu.override.yml up -d
#
# Optional: Create an alias for convenience
#   alias docker-compose-gpu='docker compose -f docker-compose.yml -f docker-compose.gpu.override.yml'
# ============================================================================

services:
  ollama:
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [ gpu ]