Skip to main content
Glama
gpu_compute.yaml619 B
auto_create: true container_name: gpu_compute description: GPU计算环境 environment: CUDA_VISIBLE_DEVICES: all NVIDIA_VISIBLE_DEVICES: all gpus: all image: nvidia/cuda:11.3-devel-ubuntu20.04 install_packages: - python3 - python3-pip - git - vim memory_limit: 32g network_mode: host privileged: true restart_policy: always setup_commands: - apt update && apt install -y python3 python3-pip git vim - pip3 install numpy torch torchvision - nvidia-smi - echo 'GPU compute environment ready!' shm_size: 16g template_type: ml volumes: - /data:/data - /home:/home - /workspace:/workspace working_directory: /workspace

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/maricoxu/remote-terminal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server