Modal Serverless GPU

# Single GPU
@app.function(gpu="A100")

# Specific memory variant
@app.function(gpu="A100-80GB")

# Multiple GPUs (up to 8)
@app.function(gpu="H100:4")

# GPU with fallbacks
@app.function(gpu=["H100", "A100", "L40S"])

# Any available GPU
@app.function(gpu="any")

# Basic image with pip
image = modal.Image.debian_slim(python_version="3.11").pip_install(
    "torch==2.1.0", "transformers==4.36.0", "accelerate"
)

# From CUDA base
image = modal.Image.from_registry(
    "nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04",
    add_python="3.11"
).pip_install("torch", "transformers")

# With system packages
image = modal.Image.debian_slim().apt_install("git", "ffmpeg").pip_install("whisper")

volume = modal.Volume.from_name("model-cache", create_if_missing=True)

@app.function(gpu="A10G", volumes={"/models": volume})
def load_model():
    import os
    model_path = "/models/llama-7b"
    if not os.path.exists(model_path):
        model = download_model()
        model.save_pretrained(model_path)
        volume.commit()  # Persist changes
    return load_from_path(model_path)

@app.function()
@modal.fastapi_endpoint(method="POST")
def predict(text: str) -> dict:
    return {"result": model.predict(text)}

from fastapi import FastAPI
web_app = FastAPI()

@web_app.post("/predict")
async def predict(text: str):
    return {"result": await model.predict.remote.aio(text)}

@app.function()
@modal.asgi_app()
def fastapi_app():
    return web_app

@app.function()
@modal.batched(max_batch_size=32, wait_ms=100)
async def batch_predict(inputs: list[str]) -> list[dict]:
    # Inputs automatically batched
    return model.batch_predict(inputs)

# Create secret
modal secret create huggingface HF_TOKEN=hf_xxx

@app.function(secrets=[modal.Secret.from_name("huggingface")])
def download_model():
    import os
    token = os.environ["HF_TOKEN"]

@app.function(schedule=modal.Cron("0 0 * * *"))  # Daily midnight
def daily_job():
    pass

@app.function(schedule=modal.Period(hours=1))
def hourly_job():
    pass

@app.function(
    container_idle_timeout=300,  # Keep warm 5 min
    allow_concurrent_inputs=10,  # Handle concurrent requests
)
def inference():
    pass

@app.cls(gpu="A100")
class Model:
    @modal.enter()  # Run once at container start
    def load(self):
        self.model = load_model()  # Load during warm-up

    @modal.method()
    def predict(self, x):
        return self.model(x)

@app.function()
def process_item(item):
    return expensive_computation(item)

@app.function()
def run_parallel():
    items = list(range(1000))
    # Fan out to parallel containers
    results = list(process_item.map(items))
    return results

@app.function(
    gpu="A100",
    memory=32768,              # 32GB RAM
    cpu=4,                     # 4 CPU cores
    timeout=3600,              # 1 hour max
    container_idle_timeout=120,# Keep warm 2 min
    retries=3,                 # Retry on failure
    concurrency_limit=10,      # Max concurrent containers
)
def my_function():
    pass

# Test locally
if __name__ == "__main__":
    result = my_function.local()

# View logs
# modal app logs my-app