Introduce support for dynamic batching

[baijumeswani]

The changes in #1580 introduce a new API in onnxruntime-genai that enables continuous submission of requests to a generation engine. Internally, the scheduler statically batches these requests, allowing the API to interface seamlessly with models designed for static batching.

This pull request lays the groundwork for dynamic request batching by incorporating concepts from vLLM. Specifically, it implements a block-based key-value cache manager.

To support dynamic batching, the underlying model must handle variable-length inputs (as opposed to fixed-size static batches) and leverage the PagedAttention contrib-op.

To run the continuous batching example:

python continuous-batching.py -m models/phi-3.5-paged/ -e cuda -n 100
100%|███████████████████████████████████████████████████████████████████████| 100/100 [00:09<00:00, 11.07it/s]
⌛ Tokens per second: 2630.78

[baijumeswani]

Thank you for the review. :)