fix(CRITICAL): engine death on image request + stop overwriting base corex modules

Root cause from latest docker build log:
  ValueError: You set image=0 in --limit-mm-per-prompt, but found 1 items
  → Engine background task crashes → AsyncEngineDeadError → all subsequent 503

Fixes:
1. computility-run.yaml: add --limit-mm-per-prompt image=1
   Prevents multimodal ValueError from killing the engine process.

2. patch_ops.sh: DON'T overwrite base image's corex_gdn.py/corex_moe.py
   Comp 168 log proves base image's corex modules work with libcorex_gdn.so.
   Our overwrite broke CoreXGDN.__init__ (unexpected kwarg 'num_v_heads').
   Only deploy ours if base has NO corex modules at all.
   Also deploy corex_fa2.py if base lacks it.

3. qwen3_5.py: try multiple CoreXGDN init signatures
   Base image CoreXGDN may accept different kwargs than ours.
   Try kwargs form first, fall back to positional.

4. corex_gdn.py: accept both calling conventions in __init__
   Future-proof for when we DO need to deploy ours.

5. Copied upstream_ref headers: ilu_layer_fused_moe.h, ilu_layer_attention.h
   Last 2 missing ILU files from xllm. All 14/14 now present.

qwen3_6_scripts/patch_ops.sh

@@ -180,17 +180,34 @@ if [ -n "$VLLM2" ]; then
     cp ./chat_utils.py "$VLLM2/entrypoints/chat_utils.py" 2>/dev/null || true
 fi
 
-# Deploy corex_gdn.py + corex_moe.py → vllm model_executor/models/
-# These provide the fused GDN prefill kernel and MoE pipeline that competitor 168 had
-if [ -f "/workspace/ex_engine/python/corex_gdn.py" ]; then
+# corex_gdn.py + corex_moe.py: DO NOT overwrite base image originals!
+# Comp 168 log proves: base image's corex_gdn.py loads libcorex_gdn.so and works.
+# Our overwrite breaks the interface (CoreXGDN.__init__ signature mismatch).
+# Only deploy ours if base has NO corex modules at all.
+if [ ! -f "$VLLM/model_executor/models/corex_gdn.py" ]; then
     cp "/workspace/ex_engine/python/corex_gdn.py" "$VLLM/model_executor/models/corex_gdn.py" 2>/dev/null || true
+    echo "[patch_ops] corex_gdn.py deployed (base had none)"
+fi
+if [ ! -f "$VLLM/model_executor/models/corex_moe.py" ]; then
     cp "/workspace/ex_engine/python/corex_moe.py" "$VLLM/model_executor/models/corex_moe.py" 2>/dev/null || true
-    echo "[patch_ops] Deployed: corex_gdn.py + corex_moe.py → $VLLM/model_executor/models/"
-    if [ -n "$VLLM2" ]; then
-        cp "/workspace/ex_engine/python/corex_gdn.py" "$VLLM2/model_executor/models/corex_gdn.py" 2>/dev/null || true
-        cp "/workspace/ex_engine/python/corex_moe.py" "$VLLM2/model_executor/models/corex_moe.py" 2>/dev/null || true
+    echo "[patch_ops] corex_moe.py deployed (base had none)"
+fi
+# corex_fa2.py: deploy if base doesn't have it
+# Comp 168 log: corex_fa2.py provides FA2 packed/paged/chunked dispatch
+if [ ! -f "$VLLM/model_executor/models/corex_fa2.py" ]; then
+    if [ -f "/workspace/ex_engine/python/corex_fa2.py" ]; then
+        cp "/workspace/ex_engine/python/corex_fa2.py" "$VLLM/model_executor/models/corex_fa2.py" 2>/dev/null || true
+        echo "[patch_ops] corex_fa2.py deployed (base had none)"
     fi
 fi
+echo "[patch_ops] CoreX modules: preserved base originals where they exist"
+if [ -n "$VLLM2" ]; then
+    for _CM in corex_gdn.py corex_moe.py corex_fa2.py; do
+        if [ -f "$VLLM/model_executor/models/$_CM" ] && [ ! -f "$VLLM2/model_executor/models/$_CM" ]; then
+            cp "$VLLM/model_executor/models/$_CM" "$VLLM2/model_executor/models/$_CM" 2>/dev/null || true
+        fi
+    done
+fi
 
 # Deploy EX Engine Python module + C++ bridge into vllm importable path
 EX_ENGINE_SRC="/workspace/ex_engine"

qwen3_6_scripts/qwen3_5.py

@@ -463,6 +463,7 @@ class GatedDeltaNet(nn.Module):
         self._use_corex_gdn = False
         if _corex_gdn_available and _corex_gdn_module is not None:
             try:
+                # Try base image's CoreXGDN signature first (may differ from ours)
                 self._corex_gdn_obj = _corex_gdn_module.CoreXGDN(
                     num_v_heads=self.num_v_heads // tp_size,
                     num_k_heads=self.num_k_heads // tp_size,
@@ -472,11 +473,25 @@ class GatedDeltaNet(nn.Module):
                     layer_idx=layer_idx,
                 )
                 self._use_corex_gdn = True
-                logger.info("GatedDeltaNet layer %d: CoreX fused GDN enabled", layer_idx)
+            except TypeError:
+                # Fallback: simpler signature
+                try:
+                    self._corex_gdn_obj = _corex_gdn_module.CoreXGDN(
+                        self.num_v_heads // tp_size,
+                        self.head_k_dim,
+                        layer_idx=layer_idx,
+                    )
+                    self._use_corex_gdn = True
+                except Exception as e2:
+                    logger.warning(
+                        "GatedDeltaNet layer %d: CoreX GDN init failed (%s), PyTorch",
+                        layer_idx, e2)
             except Exception as e:
                 logger.warning(
-                    "GatedDeltaNet layer %d: CoreX GDN init failed (%s), using PyTorch",
+                    "GatedDeltaNet layer %d: CoreX GDN init failed (%s), PyTorch",
                     layer_idx, e)
+            if self._use_corex_gdn and layer_idx == 0:
+                logger.info("GatedDeltaNet: CoreX fused GDN enabled")
 
     def _conv1d_weight_loader(self, param: torch.Tensor,
                               loaded_weight: torch.Tensor) -> None: