Modal 使用示例

# 科学计算的常见模式 ## 机器学习模型推理 ### 基础模型服务 python import modal app = modal.App("ml-inference") image = ( modal.Image.debian_slim() .uv_pip_install("torch", "transformers") ) @app.cls( image=image, gpu="L40S", ) class Model: @modal.enter() def load_model(self): from transformers import AutoModel, AutoTokenizer self.model = AutoModel.from_pretrained("bert-base-uncased") self.tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") @modal.method() def predict(self, text: str): inputs = self.tokenizer(text, return_tensors="pt") outputs = self.model(**inputs) return outputs.last_hidden_state.mean(dim=1).tolist() @app.local_entrypoint() def main(): model = Model() result = model.predict.remote("Hello world") print(result) ### 使用 Volume 的模型服务 python volume = modal.Volume.from_name("models", create_if_missing=True) MODEL_PATH = "/models" @app.cls( image=image, gpu="A100", volumes={MODEL_PATH: volume} ) class ModelServer: @modal.enter() def load(self): import torch self.model = torch.load(f"{MODEL_PATH}/model.pt") self.model.eval() @modal.method() def infer(self, data): import torch with torch.no_grad(): return self.model(torch.tensor(data)).tolist() ## 批处理 ### 并行数据处理 python @app.function( image=modal.Image.debian_slim().uv_pip_install("pandas", "numpy"), cpu=2.0, memory=8192 ) def process_batch(batch_id: int): import pandas as pd # 加载批次 df = pd.read_csv(f"s3://bucket/batch_{batch_id}.csv") # 处理 result = df.apply(lambda row: complex_calculation(row), axis=1) # 保存结果 result.to_csv(f"s3://bucket/results_{batch_id}.csv") return batch_id @app.local_entrypoint() def main(): # 并行处理 100 个批次 results = list(process_batch.map(range(100))) print(f"Processed {len(results)} batches") ### 带进度的批处理 python @app.function() def process_item(item_id: int): # 昂贵的处理过程 result = compute_something(item_id) return result @app.local_entrypoint() def main(): items = list(range(1000)) print(f"Processing {len(items)} items...") results = [] for i, result in enumerate(process_item.map(items)): results.append(resul