[XPU] Enable NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 on Intel XPU backend (#24390)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Yao Matrix <matrix.yao@intel.com>

.gitignore

@@ -270,6 +270,11 @@ sgl-kernel/csrc/**/*_musa/
 # MUSA core dump files
 *.mudmp
 
+# Local-only XPU test: Nemotron-3 Nano 30B-A3B is too large to run in CI
+# (requires tp=4; no 4-GPU XPU runner). Kept on disk for local development,
+# never tracked/pushed.
+test/registered/xpu/test_nvidia_nemotron_3_nano.py
+
 # Others
 # diffusion 3D outputs
 *.glb