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/.gitignore

@@ -0,0 +1,61 @@
+# Visual Studio Code
+/.vscode*
+
+# Idea
+/.idea
+/cmake-build-debug/
+/cmake-build-release/
+
+# CMake
+/build*
+
+# vcpkg
+/.vcpkg*
+
+# cache
+/.*cache
+
+# deps
+/.deps
+
+# libtorch
+/libtorch
+
+# tests
+/Testing*
+
+# rust
+Cargo.lock
+
+
+# distribution / packaging
+.Python
+build/
+dist/
+eggs/
+.eggs/
+sdist/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Python module builds
+*.egg-info/
+xllm/*.pyd
+xllm/*.so
+xllm/version.py
+__pycache__/
+.pkl_memoize_py3/
+
+# compile_commands.json from nvbench
+compile_commands.json
+
+# ascend kernel meta files
+/kernel_meta
+
+# local files
+/local
+/logs
+/log