[CPU] Add support for Gemma4 on Xeon (#22498)

Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: jianan-gu <jianan.gu@intel.com>
Co-authored-by: Haotong Zou <haotong.zou@intel.com>

python/sglang/srt/server_args.py

@@ -5635,13 +5635,19 @@ class ServerArgs:
             # Default attention backend selection moved to the override registry
             # (arg_groups/overrides.py: _gemma4_overrides).
             prefill_backend, decode_backend = self._resolved_attention_backends()
-            accepted_backends = ("trtllm_mha", "triton", "ascend", "intel_xpu")
+            accepted_backends = (
+                "trtllm_mha",
+                "triton",
+                "ascend",
+                "intel_xpu",
+                "intel_amx",
+            )
             assert (
                 prefill_backend in accepted_backends
                 and decode_backend in accepted_backends
             ), (
-                "Gemma4 only supports trtllm_mha, triton, or intel_xpu attention backend, "
-                f"got prefill={prefill_backend}, decode={decode_backend}"
+                "Gemma4 only supports trtllm_mha, triton, ascend, intel_xpu, or intel_amx "
+                f"attention backend, got prefill={prefill_backend}, decode={decode_backend}"
             )
 
             # The quantization/moe_runner_backend resolution moved to the override