Fix eager AMX backend probe imports (#34496)

Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>

python/sglang/multimodal_gen/runtime/utils/common.py

@@ -398,14 +398,15 @@ def get_bool_env_var(name: str, default: str = "false") -> bool:
     return value in truthy_values
 
 
-try:
-    import sgl_kernel  # noqa: F401
+@lru_cache(maxsize=1)
+def _is_intel_amx_backend_available():
+    try:
+        import sgl_kernel  # noqa: F401
+
+        return hasattr(torch.ops.sgl_kernel, "convert_weight_packed")
+    except Exception:
+        return False
 
-    is_intel_amx_backend_available = hasattr(
-        torch.ops.sgl_kernel, "convert_weight_packed"
-    )
-except:
-    is_intel_amx_backend_available = False
 
 try:
     # move torch.cpu._is_amx_tile_supported() from cpu_has_amx_support
@@ -416,7 +417,7 @@ except:
 
 
 def cpu_has_amx_support():
-    return is_amx_tile_supported and is_intel_amx_backend_available
+    return is_amx_tile_supported and _is_intel_amx_backend_available()
 
 
 def use_intel_amx_backend(layer):

python/sglang/srt/utils/common.py

@@ -316,14 +316,15 @@ def is_sm121() -> bool:
     return is_cuda() and torch.cuda.get_device_capability() == (12, 1)
 
 
-try:
-    import sgl_kernel  # noqa: F401
+@lru_cache(maxsize=1)
+def _is_intel_amx_backend_available():
+    try:
+        import sgl_kernel  # noqa: F401
+
+        return hasattr(torch.ops.sgl_kernel, "convert_weight_packed")
+    except Exception:
+        return False
 
-    is_intel_amx_backend_available = hasattr(
-        torch.ops.sgl_kernel, "convert_weight_packed"
-    )
-except:
-    is_intel_amx_backend_available = False
 
 try:
     # move torch.cpu._is_amx_tile_supported() from cpu_has_amx_support
@@ -334,7 +335,7 @@ except:
 
 
 def cpu_has_amx_support():
-    return is_amx_tile_supported and is_intel_amx_backend_available
+    return is_amx_tile_supported and _is_intel_amx_backend_available()
 
 
 def use_intel_amx_backend(layer):