data: port complete MoE + xllm layer call chains from upstream repos

MoE call chain from ds_vllm (vllm-project/vllm latest):
  ex_engine/moe/ — 20 files, 8736 lines
  - modular_kernel.py (1630 lines) — base classes for modular MoE
  - experts/fused_batched_moe.py (972 lines) — NaiveBatchedExperts
  - prepare_finalize/batched.py (171 lines) — token grouping by expert
  - topk_weight_and_reduce.py (176 lines) — scatter-add finalize
  - fused_moe.py (1740 lines) — main fused_moe dispatch
  - config.py (1407 lines) — FusedMoEQuantConfig
  - activation.py, utils.py, layer.py, etc.

xllm layer code (jd-opensource/xllm):
  ex_engine/xllm_layers/ — 39 files, 5859 lines
  - ilu/fused_moe.cpp (797 lines) — production ixformer 7-step MoE pipeline
  - ilu/attention.cpp (189 lines) — paged_attention + flash_attn bridge
  - npu_torch/qwen3_gated_delta_net_base.cpp (576 lines) — GDN reference
  - common/rms_norm.cpp, rotary_embedding.cpp, activation.cpp, dense_mlp.cpp

xllm ILU kernels — synced 10 files to upstream (diffs from prior edits)

These are reference implementations, NOT hand-written.
Source repos: vllm-project/vllm, jd-opensource/xllm

ex_engine/moe/prepare_finalize/__init__.py

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from vllm.model_executor.layers.fused_moe.prepare_finalize.batched import (
+    BatchedPrepareAndFinalize,
+)
+from vllm.model_executor.layers.fused_moe.prepare_finalize.naive_dp_ep import (
+    MoEPrepareAndFinalizeNaiveDPEPModular,
+    MoEPrepareAndFinalizeNaiveDPEPMonolithic,
+    make_moe_prepare_and_finalize_naive_dp_ep,
+)
+from vllm.model_executor.layers.fused_moe.prepare_finalize.no_dp_ep import (
+    MoEPrepareAndFinalizeNoDPEPModular,
+    MoEPrepareAndFinalizeNoDPEPMonolithic,
+    make_moe_prepare_and_finalize_no_dp_ep,
+)
+
+__all__ = [
+    "BatchedPrepareAndFinalize",
+    "MoEPrepareAndFinalizeNaiveDPEPMonolithic",
+    "MoEPrepareAndFinalizeNaiveDPEPModular",
+    "make_moe_prepare_and_finalize_naive_dp_ep",
+    "MoEPrepareAndFinalizeNoDPEPMonolithic",
+    "MoEPrepareAndFinalizeNoDPEPModular",
+    "make_moe_prepare_and_finalize_no_dp_ep",
+    # deepep_ht, deepep_ll, and flashinfer_a2a are not
+    # imported here as they have optional dependencies (deep_ep, flashinfer).
+    # Import them directly from their modules as needed.
+]