feat: ex_factor_0.so ctypes桥接 + ex_engine package部署

1. ex_topk_bridge.py (100行):
   ctypes.CDLL加载ex_factor_0.so → ex_dispatch_moe_topk_softmax()
   CCCL warp-shuffle kernel, 零SMEM, 64 experts × topk=8

2. _custom_ops.py topk_softmax调用链新增Priority 1:
   P0: ix_bridge → ixformer::infer
   P1: ex_factor_0.so → CCCL warp kernel  ← NEW
   P2: _moe_C.so → vllm v0.5.5 kernel
   P3: moe_topk_softmax_v3.so → 自编译kernel

3. patch_ops.sh补齐ex_engine package部署:
   ex_engine/python/*.py + build/*.so → site-packages/ex_engine/

qwen3_6_scripts/_custom_ops.py

@@ -1114,7 +1114,18 @@ def topk_softmax(topk_weights: torch.Tensor, topk_ids: torch.Tensor,
         except Exception as e:
             logger.warning("topk_softmax ix_bridge failed (%s), trying CUDA kernel", e)
 
-    # Priority 1: CUDA kernel (_moe_C or moe_topk_softmax_v3)
+    # Priority 1: ex_factor_0.so → CCCL warp-shuffle topk kernel (compiled for BI-V100)
+    try:
+        from ex_engine.python.ex_topk_bridge import ex_topk_softmax as _ex_topk
+        gating = gating_output if isinstance(gating_output, torch.Tensor) else gating_output
+        _ex_topk(topk_weights, topk_ids, token_expert_indicies, gating.float())
+        return
+    except Exception as e:
+        if not getattr(topk_softmax, '_ex_warned', False):
+            logger.warning("ex_factor_0 topk failed (%s), trying _moe_C", e)
+            topk_softmax._ex_warned = True
+
+    # Priority 2: CUDA kernel (_moe_C or moe_topk_softmax_v3)
     if _moe_topk_ext is not None:
         try:
             gating = gating_output if isinstance(gating_output, torch.Tensor) else gating_output

qwen3_6_scripts/patch_ops.sh

@@ -337,6 +337,25 @@ if [[ -n "$VLLM2" ]]; then
     echo "[ok] mirrored all patches to VLLM2"
 fi
 
+build_stage "deploying ex_engine package to Python path"
+_SITE=""
+for _s in /usr/local/corex/lib64/python3/dist-packages \
+          /usr/local/corex/lib/python3/dist-packages \
+          /usr/local/lib/python3.10/site-packages; do
+    [[ -d "$_s" ]] && _SITE="$_s" && break
+done
+if [[ -n "$_SITE" ]]; then
+    _EX_DST="$_SITE/ex_engine"
+    mkdir -p "$_EX_DST/python" "$_EX_DST/build"
+    touch "$_EX_DST/__init__.py" "$_EX_DST/python/__init__.py"
+    cp /workspace/ex_engine/python/*.py "$_EX_DST/python/" 2>/dev/null || true
+    if [[ -d /workspace/ex_engine/build ]]; then
+        cp /workspace/ex_engine/build/*.so "$_EX_DST/build/" 2>/dev/null || true
+        cp /workspace/ex_engine/build/*.so "$_EX_DST/" 2>/dev/null || true
+    fi
+    echo "[ok] ex_engine deployed to $_EX_DST ($(ls "$_EX_DST/build/"*.so 2>/dev/null | wc -l) .so files)"
+fi
+
 build_stage "compiling submission Python sources"
 find . -path './wheels' -prune -o -name '*.py' -print0 | xargs -0 python3 -m py_compile 2>&1 || echo "[WARN] some .py files failed to compile (non-fatal)"
 build_stage "patch script completed"