feat: add IQP / IQP-Z latency and throughput benchmark

[viiccwen]

Related Issues

Closes #1256

Changes

• Bug fix
• New feature
• Refactoring
• Documentation
• Test
• CI/CD pipeline
• Other

Why

QDP already supports iqp and iqp-z in the encoding engine, but the standard latency / throughput benchmark path did not. The Rust synthetic pipeline still treated those runs like amplitude-shaped inputs, and the Python benchmark layer did not expose or document the IQP-family options clearly.

This meant users could not benchmark IQP-family encodings through the same benchmark API/scripts used for amplitude.

How

• updated qdp-core synthetic benchmark sizing so:
  • iqp-z uses num_qubits
  • iqp uses num_qubits + num_qubits * (num_qubits - 1) / 2
• generated deterministic IQP-family phase parameters in the Rust and Python synthetic benchmark helpers
• added iqp / iqp-z support to:
  • benchmark_latency.py
  • benchmark_throughput.py
  • benchmark_pytorch_ref.py
• extended the PyTorch fallback path to accept iqp-z
• added Rust and Python tests covering:
  • pipeline vector sizing
  • deterministic IQP-family sample generation
  • fallback benchmark execution
• updated benchmark and Python API documentation

NOTICED: Due to #1252, we only can testing Mahout IQP/IQP-Z, using TODO label and warning to fix it in the future.

Results

Generating 12800 samples of 16 qubits...
  Batch size   : 64
  Vector length: 136
  Batches      : 200
  Prefetch     : 16
  Frameworks   : mahout
  Encode method: iqp
  Generated 12800 samples
  PennyLane/Qiskit format: 13.28 MB
  Mahout format: 13.28 MB

======================================================================
DATA-TO-STATE LATENCY BENCHMARK: 16 Qubits, 12800 Samples
======================================================================

[Mahout] Full Pipeline (DataLoader -> GPU)...
  Total Time: 0.5072 s (0.040 ms/vector)

======================================================================
LATENCY (Lower is Better)
Samples: 12800, Qubits: 16
======================================================================
Mahout                  0.040 ms/vector
----------------------------------------------------------------------

Checklist

• Added or updated unit tests for all changes
• Added or updated documentation for all changes

[400Ping]

Overall LGTM

[400Ping]

Note that I only did a quick scan for this PR, a little busy this week