Skip to content

⚙️ Inference Engines

Powerful Model Execution Engines

Synchronous and asynchronous inference with advanced features

🚀 Engine Types

Synchronous Engine

from llm_evaluation_framework.model_inference_engine import ModelInferenceEngine

engine = ModelInferenceEngine(registry)
results = engine.evaluate_model(model_name, test_cases, use_case)

Asynchronous Engine

from llm_evaluation_framework.engines.async_inference_engine import AsyncInferenceEngine

async_engine = AsyncInferenceEngine(registry)
results = await async_engine.evaluate_model_async(model_name, test_cases, use_case)

📊 Performance Optimization

  • Batch Processing: Process multiple requests efficiently
  • Concurrent Execution: Run async evaluations
  • Caching: Cache results for repeated queries
  • Rate Limiting: Respect API limits

Learn More