[BugFix] skip combo kernel on cpu (vllm-project#29129)

Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>

Author: BoyuanFeng

vllm/config/compilation.py

@@ -664,6 +664,8 @@ def __post_init__(self) -> None:
             is_torch_equal_or_newer("2.9.0.dev")
             and "combo_kernels" not in self.inductor_compile_config
             and "benchmark_combo_kernel" not in self.inductor_compile_config
+            # (fixme @boyuan) combo kernel does not support cpu yet.
+            and not current_platform.is_cpu()
         ):
             # use horizontal fusion, which is useful for fusing qk-norm and
             # qk-rope when query and key have different shapes.