b3a0c78903
- Add Plugin GPU Quota config section to scheduler.yaml.example - Add audit logging config to homelab-secure.yaml (HIPAA-compliant) - Add Jupyter and vLLM plugin configs to all worker configs: - Security settings (passwords, trusted channels, blocked packages) - Resource limits (GPU, memory, CPU) - Model cache paths and quantization options for vLLM - Disable plugins in HIPAA deployment mode for compliance - Update deployments README with plugin services and GPU quotas
87 lines
1.8 KiB
YAML
87 lines
1.8 KiB
YAML
worker_id: "local-worker"
|
|
base_path: "data/dev/experiments"
|
|
train_script: "train.py"
|
|
|
|
redis_url: "redis://localhost:6379/0"
|
|
|
|
local_mode: true
|
|
|
|
prewarm_enabled: false
|
|
|
|
max_workers: 2
|
|
poll_interval_seconds: 2
|
|
|
|
auto_fetch_data: false
|
|
|
|
data_manager_path: "./data_manager"
|
|
dataset_cache_ttl: "30m"
|
|
|
|
data_dir: "data/dev/active"
|
|
|
|
snapshot_store:
|
|
enabled: false
|
|
|
|
podman_image: "python:3.9-slim"
|
|
container_workspace: "/workspace"
|
|
container_results: "/results"
|
|
gpu_devices: []
|
|
gpu_vendor: "apple"
|
|
gpu_visible_devices: []
|
|
|
|
# Apple M-series GPU configuration
|
|
apple_gpu:
|
|
enabled: true
|
|
metal_device: "/dev/metal"
|
|
mps_runtime: "/dev/mps"
|
|
|
|
resources:
|
|
max_workers: 2
|
|
desired_rps_per_worker: 2
|
|
podman_cpus: "2"
|
|
podman_memory: "4Gi"
|
|
|
|
metrics:
|
|
enabled: false
|
|
|
|
queue:
|
|
type: "native"
|
|
native:
|
|
data_dir: "data/dev/queue"
|
|
|
|
# Plugin Configuration (for local development)
|
|
plugins:
|
|
# Jupyter Notebook/Lab Service
|
|
jupyter:
|
|
enabled: true
|
|
image: "quay.io/jupyter/base-notebook:latest"
|
|
default_port: 8888
|
|
mode: "lab"
|
|
# Security settings
|
|
security:
|
|
trusted_channels:
|
|
- "conda-forge"
|
|
- "defaults"
|
|
blocked_packages: [] # Less restrictive for local dev
|
|
require_password: false # No password for local dev
|
|
# Resource limits
|
|
max_gpu_per_instance: 1
|
|
max_memory_per_instance: "4Gi"
|
|
|
|
# vLLM Inference Service
|
|
vllm:
|
|
enabled: true
|
|
image: "vllm/vllm-openai:latest"
|
|
default_port: 8000
|
|
# Model cache location
|
|
model_cache: "data/dev/models"
|
|
# Supported quantization methods: awq, gptq, fp8, squeezellm
|
|
default_quantization: "" # No quantization for dev (better quality)
|
|
# Resource limits
|
|
max_gpu_per_instance: 1
|
|
max_model_len: 2048
|
|
tensor_parallel_size: 1
|
|
|
|
task_lease_duration: "30m"
|
|
heartbeat_interval: "1m"
|
|
max_retries: 3
|
|
graceful_timeout: "5m"
|