ref(upstream): FULL TREE — Deep-Spark xllm (1470) + ds_vllm csrc/models (703)

Replaces cherry-picked upstream_ref with complete source trees.

xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files)
  Complete: kernels → layers → models → runtime → scheduler → api
  Excluded: .git, binary images, third_party submodule checkouts

ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files)
  Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops
  Excluded: tests, benchmarks, docs, examples (not needed for reference)

Critical call chains now fully traceable:
  MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer
  GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp
  Attention: ixformer.h → xllm_paged_attention → attention.cpp

upstream_ref/xllm/.pre-commit-config.yaml

@@ -0,0 +1,11 @@
+# pre-commit install
+# pre-commit run --all-files
+
+repos:
+-   repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: v20.1.6
+    hooks:
+      - id: clang-format
+        types_or: [c++, c, cuda]
+        exclude: ^(cibuild/|tools/|third_party/|cmake/|build/|.*\.ptx\.h$)
+