[AINode] Preliminary version of concurrent inference

[jtmer]

Description

This PR adds an request–pooling engine for multi-request inference on time-series models such as TimerXL. The change set introduces three core Python modules—requestpool.py, request.py, and utils.py—plus a self-contained benchmark harness (guarded by if name == "main":) to compare pooled vs. baseline generation speed and numerical fidelity.

Design

Overlap multiple user requests on one device: RequestPool.step() batches all ready requests every 15 ms if there are no requests running, and feeds a single forward pass to the model.
Handle variable sequence lengths: Left-padding to max_len per tensor type; preserves causal semantics while enabling torch.cat.

Behavior & configuration

RequestPool.add_request truncates inputs that are not an exact multiple of config.input_token_len, ensuring model state alignment;
Oversized write attempts are silently clipped to max_new_steps;

Class & method organization

RequestPool
Public API: add_request, run_inference (starts loop), step (single scheduling + forward pass).
Request
id, chunk_size, …, state, cur_step_idx, output_tensor
write_step_output pre-allocates and in-place fills a fixed buffer—no Python-side reallocation after start.
utils
split_moe_output Slices Moe[Causal]LMOutputWithPast into per-request objects.

---

This PR has:

• been self-reviewed.
• added comments explaining the "why" and the intent of the code wherever would not be obvious
  for an unfamiliar reader.
• added unit tests.

---

Key changed/added classes (or packages if there are too many classes) in this PR

ainode.core.inference.requestpool.RequestPool
ainode.core.inference.request.Request
ainode.core.inference.utils.split_moe_output