feat: ix_moe_bridge + ix_attn_bridge — dlopen bridges for full ixformer::infer API

Bridge architecture (from xllm/core/kernels/ilu/ixformer.h):

ix_moe_bridge.so (MoE 7-step fused pipeline):
  - topk_softmax → moe_compute_token_index_api → moe_expand_input
  - moe_w16a16_group_gemm (x2) → silu_and_mul → moe_output_reduce_sum
  - fused_moe_forward(): replaces entire Python expert loop
  - Fix: group_gemm format NT→TN (match xllm trans_b=true)

ix_attn_bridge.so (attention + linear):
  - ixinfer_flash_attn_unpad_with_block_tables (fused prefill)
  - xllm_paged_attention (fused paged decode)
  - ixformer_linear (matmul + activation)
  - residual_rms_norm (fused residual + norm)

Integration:
  - ix_fused_moe.py: Python loader (prebuilt .so → JIT → unavailable)
  - qwen3_5.py: Tier 0 dispatch in _pure_pytorch_experts()
  - patch_ops.sh: deploys ix_fused_moe.py + all prebuilt/*.so

Source: jd-opensource/xllm (fresh clone, all ILU kernels verified SAME)
Sync: upstream_ref/xllm_latest/models/llm/qwen3_next_hybrid_base.h (+32 lines)

Build on real machine:
  bash qwen3_6_scripts/build_ix_moe_bridge.sh
  bash qwen3_6_scripts/build_ix_attn_bridge.sh

qwen3_6_scripts/patch_ops.sh

@@ -185,8 +185,20 @@ build_stage "installing vLLM Qwen3.6 model implementation"
 # --- vllm model: Qwen3.6-35B-A3B (Qwen3_5 MoE arch) -------------------------
 cp ./mamba_cache.py "${VLLM_ROOT}/model_executor/models/"
 cp ./qwen3_5.py "${VLLM_ROOT}/model_executor/models/qwen3_5.py"
+cp ./ix_fused_moe.py "${VLLM_ROOT}/model_executor/models/ix_fused_moe.py" || true
 python3 ./patch_vllm_qwen3_5.py
 
+# --- Deploy prebuilt .so into vllm package for import -----------------------
+PREBUILT_DIR="./prebuilt/corex-3.2.3-ivcore10"
+if [ -d "$PREBUILT_DIR" ]; then
+    for so_file in "$PREBUILT_DIR"/*.so; do
+        base=$(basename "$so_file" .so)
+        # Deploy corex_*.so as vllm submodules (import from vllm import corex_xxx)
+        cp "$so_file" "${VLLM_ROOT}/${base}.so" 2>/dev/null || true
+        echo "[patch_ops] deployed ${base}.so → ${VLLM_ROOT}/"
+    done
+fi
+
 # --- sequence.py: fix completion_tokens inflation under chunked prefill ------
 # Bug: get_output_token_ids_to_return(delta=True) with num_new_tokens=0
 # returns _cached_all_token_ids[-0:] == [0:] (the ENTIRE prompt+output list).