Vast.ai Deploy Integration
Overview
Deploy ML training jobs and inference services on Vast.ai GPU cloud. Covers Docker image optimization, automated provisioning scripts, data transfer strategies, and deployment automation.
Prerequisites
- Vast.ai CLI authenticated
- Docker image published to a registry
- Training/inference code tested locally
Instructions
Step 1: Optimized Docker Image
# Dockerfile.vastai — optimized for fast pulls on Vast.ai
FROM pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime
# Install dependencies in a single layer
COPY requirements.txt /tmp/
RUN pip install --no-cache-dir -r /tmp/requirements.txt && rm /tmp/requirements.txt
# Copy application code
COPY src/ /workspace/src/
COPY scripts/ /workspace/scripts/
WORKDIR /workspace
CMD ["python", "src/train.py"]
# Build and push
docker build -t ghcr.io/yourorg/training:v1 -f Dockerfile.vastai .
docker push ghcr.io/yourorg/training:v1
Step 2: Automated Deployment Script
#!/usr/bin/env python3
"""deploy.py — Automated Vast.ai deployment with monitoring."""
import subprocess, json, time, argparse, sys
def deploy(args):
# Search for matching offer
query = (f"num_gpus={args.gpus} gpu_name={args.gpu} "
f"reliability>{args.reliability} dph_total<={args.max_price} "
f"disk_space>={args.disk} rentable=true")
offers = json.loads(subprocess.run(
["vastai", "search", "offers", query, "--order", "dph_total",
"--raw", "--limit", "5"],
capture_output=True, text=True, check=True).stdout)
if not offers:
print(f"ERROR: No offers matching: {query}", file=sys.stderr)
sys.exit(1)
offer = offers[0]
print(f"Selected: {offer['gpu_name']} ${offer['dph_total']:.3f}/hr "
f"(ID: {offer['id']})")
# Create instance
cmd = ["vastai", "create", "instance", str(offer["id"]),
"--image", args.image, "--disk", str(args.disk)]
if args.onstart:
cmd.extend(["--onstart-cmd", args.onstart])
result = json.loads(subprocess.run(
cmd, capture_output=True, text=True, check=True).stdout)
instance_id = result["new_contract"]
print(f"Instance {instance_id} provisioning...")
# Wait for running
for _ in range(30):
info = json.loads(subprocess.run(
["vastai", "show", "instance", str(instance_id), "--raw"],
capture_output=True, text=True).stdout)
if info.get("actual_status") == "running":
print(f"READY: ssh -p {info['ssh_port']} root@{info['ssh_host']}")
return instance_id, info
time.sleep(10)
raise TimeoutError("Instance did not start")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--gpu", default="RTX_4090")
parser.add_argument("--gpus", type=int, default=1)
parser.add_argument("--image", required=True)
parser.add_argument("--disk", type=int, default=50)
parser.add_argument("--max-price", type=float, default=0.50)
parser.add_argument("--reliability", type=float, default=0.95)
parser.add_argument("--onstart", default="")
deploy(parser.parse_args())
