feat: real-time streaming output examples for Crusoe Managed Inference

[Sakshi3027]

What this adds

Four streaming demos for Crusoe Managed Inference covering every common streaming pattern.

Demo	What it shows
Basic streaming	Stream tokens to stdout as they arrive
Callback handler	Stream via StreamingStdOutCallbackHandler
Async streaming	Non-blocking token generation with astream
Concurrent streaming	3 prompts streamed simultaneously

Why it's useful

Streaming is essential for production LLM apps it makes responses feel instant instead of making users wait for the full output. There are currently no streaming examples in the solutions library despite it being one of the most requested patterns.

Notable result: 3 concurrent async streams completed in 0.50s.

Testing

All 4 demos run successfully. Tested locally with Groq as a drop-in replacement.

To run on Crusoe:
export CRUSOE_API_KEY="your-api-key"
python streaming.py

Related contributions

• feat: LangGraph multi-node research agent on Crusoe Managed Inference #55 — LangGraph multi-node agent
• feat: MLflow experiment tracking for Crusoe Managed Inference #56 — MLflow experiment tracking
• feat: RAG pipeline with Qdrant and sentence-transformers on Crusoe Managed Inference #57 — RAG pipeline with Qdrant
• feat: structured output and tool calling examples for Crusoe Managed Inference #58 — Structured output and tool calling