runpod-deployment

import runpod

def handler(job):
    """Basic handler - receives job, returns result."""
    job_input = job["input"]
    prompt = job_input.get("prompt", "")

    # Your inference logic here
    result = process(prompt)

    return {"output": result}

runpod.serverless.start({"handler": handler})

import runpod

def streaming_handler(job):
    """Generator for streaming responses."""
    for chunk in generate_chunks(job["input"]):
        yield {"token": chunk, "finished": False}
    yield {"token": "", "finished": True}

runpod.serverless.start({
    "handler": streaming_handler,
    "return_aggregate_stream": True
})

from openai import OpenAI

client = OpenAI(
    api_key="RUNPOD_API_KEY",
    base_url="https://api.runpod.ai/v2/ENDPOINT_ID/openai/v1",
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=100,
)

# Push code - Actions builds x86 image
git add . && git commit -m "Deploy" && git push

def select_gpu(model_params_b: float, quantized: bool = False) -> str:
    effective = model_params_b * (0.5 if quantized else 1.0)
    if effective <= 3: return "RTX_A4000"      # $0.36/hr
    if effective <= 8: return "RTX_4090"       # $0.44/hr
    if effective <= 30: return "A40"           # $0.65/hr
    if effective <= 70: return "A100_80GB"     # $1.89/hr
    return "H100_80GB"                         # $4.69/hr

import runpod

def long_task_handler(job):
    total_steps = job["input"].get("steps", 10)

    for step in range(total_steps):
        process_step(step)
        runpod.serverless.progress_update(
            job_id=job["id"],
            progress=int((step + 1) / total_steps * 100)
        )

    return {"status": "complete", "steps": total_steps}

runpod.serverless.start({"handler": long_task_handler})

import runpod
import traceback

def safe_handler(job):
    try:
        # Validate input
        if "prompt" not in job["input"]:
            return {"error": "Missing required field: prompt"}

        result = process(job["input"])
        return {"output": result}

    except torch.cuda.OutOfMemoryError:
        return {"error": "GPU OOM - reduce input size", "retry": False}
    except Exception as e:
        return {"error": str(e), "traceback": traceback.format_exc()}

runpod.serverless.start({"handler": safe_handler})

vllm_env = {
    "MODEL_NAME": "meta-llama/Llama-3.1-70B-Instruct",
    "HF_TOKEN": "${HF_TOKEN}",
    "TENSOR_PARALLEL_SIZE": "2",        # Multi-GPU
    "MAX_MODEL_LEN": "16384",
    "GPU_MEMORY_UTILIZATION": "0.95",
    "QUANTIZATION": "awq",              # Optional: awq, gptq
}

from openai import OpenAI

client = OpenAI(
    api_key="RUNPOD_API_KEY",
    base_url="https://api.runpod.ai/v2/ENDPOINT_ID/openai/v1",
)

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

import requests

url = "https://api.runpod.ai/v2/ENDPOINT_ID/run"
headers = {"Authorization": "Bearer RUNPOD_API_KEY"}

response = requests.post(url, headers=headers, json={
    "input": {"prompt": "Hello", "stream": True}
})
job_id = response.json()["id"]

# Stream results
stream_url = f"https://api.runpod.ai/v2/ENDPOINT_ID/stream/{job_id}"
with requests.get(stream_url, headers=headers, stream=True) as r:
    for line in r.iter_lines():
        if line: print(line.decode())

configs = {
    "interactive_api": {
        "workers_min": 1,      # Always warm
        "workers_max": 5,
        "idle_timeout": 120,
        "scaler_type": "QUEUE_DELAY",
        "scaler_value": 1,     # 1s latency target
    },
    "batch_processing": {
        "workers_min": 0,
        "workers_max": 20,
        "idle_timeout": 30,
        "scaler_type": "REQUEST_COUNT",
        "scaler_value": 5,
    },
    "cost_optimized": {
        "workers_min": 0,
        "workers_max": 3,
        "idle_timeout": 15,    # Aggressive scale-down
        "scaler_type": "QUEUE_DELAY",
        "scaler_value": 5,
    },
}

import runpod

async def check_health(endpoint_id: str):
    endpoint = runpod.Endpoint(endpoint_id)
    health = await endpoint.health()

    return {
        "status": health.status,
        "workers_ready": health.workers.ready,
        "queue_depth": health.queue.in_queue,
        "avg_latency_ms": health.metrics.avg_execution_time,
    }

query GetEndpoint($id: String!) {
    endpoint(id: $id) {
        status
        workers { ready running pending throttled }
        queue { inQueue inProgress completed failed }
        metrics {
            requestsPerMinute
            avgExecutionTimeMs
            p95ExecutionTimeMs
            successRate
        }
    }
}

FROM runpod/pytorch:2.1.0-py3.10-cuda12.1.1-devel-ubuntu22.04

WORKDIR /app

# Install dependencies (cached layer)
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application
COPY . .

# RunPod entrypoint
CMD ["python", "-u", "handler.py"]

def estimate_monthly_cost(gpu_type, daily_requests, avg_time_s):
    rates = {"RTX_4090": 0.44, "A40": 0.65, "A100_80GB": 1.89}
    daily_hours = (daily_requests * avg_time_s) / 3600
    return daily_hours * 30 * rates.get(gpu_type, 1.0)

# Example: 1000 requests/day, 5s each, RTX 4090
# = (1000 * 5) / 3600 * 30 * 0.44 = $18.33/month

# Install
pip install runpod

# Deploy endpoint
runpodctl project deploy --name my-endpoint --gpu-type "NVIDIA RTX 4090"

# Health check
runpod endpoint health ENDPOINT_ID

# View logs
runpod endpoint logs ENDPOINT_ID

# Scale workers
runpod endpoint scale ENDPOINT_ID --min 1 --max 10

# Local testing
python handler.py --rp_serve_api

gpu_type = "NVIDIA GeForce RTX 4090"

env = {
    "MODEL_NAME": "meta-llama/Llama-3.1-8B-Instruct",
    "MAX_MODEL_LEN": "8192",
    "GPU_MEMORY_UTILIZATION": "0.95",
}

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://api.runpod.ai/v2/ENDPOINT_ID/openai/v1",
)