fix(rollout): reject shared prefill with continuous batching

[modelpath-dev]

Why

HybridEngineRollout.generate selects the continuous path whenever SamplingConfig.continuous_batch_size is set, before any shared-prefill logic runs. With HybridEngineRolloutConfig.use_shared_prefill=True, that flag was therefore ignored with no error. This PR rejects the combination explicitly, matching the approach already taken for CUDA graph capture on the continuous path.

Fixes #8458.

Scope

• HybridEngineRollout._validate_continuous_inputs: raise ValueError when use_shared_prefill is enabled.
• Unit test for the incompatible pair.
• docs/code-docs/source/inference-engine.rst: document that shared prefill and continuous batching cannot be combined.

Out of scope: implementing shared-prefill semantics inside continuous batching.

Tradeoffs

Rejection over a compatible shared-prefill continuous mode. Continuous batching already requires n_samples_per_prompt=1, so shared prefill has no clear benefit there today.

Blast Radius

Only the experimental continuous path changes, and only when shared prefill is also requested. Default generate() and shared-prefill-only configs are unchanged.

Verification

Before the fix, _validate_continuous_inputs accepted use_shared_prefill=True with continuous_batch_size=1 (silent ignore). After the fix it raises ValueError: continuous batching does not support shared prompt prefill.

TRANSFORMERS_NO_TF=1 PYTHONPATH=. python3 -m pytest \
  tests/unit/runtime/rollout/test_hybrid_engine_rollout.py::test_continuous_generation_rejects_shared_prefill \
  tests/unit/runtime/rollout/test_hybrid_engine_rollout.py::test_continuous_generation_rejects_unsupported_inputs \
  tests/unit/runtime/rollout/test_hybrid_engine_rollout.py::test_shared_prefill_rejects_graph_capture \
  tests/unit/runtime/rollout/test_hybrid_engine_rollout.py::test_generate_uses_shared_prefill_for_multiple_samples \
  -q
# 4 passed