[torch.compile] Compile CustomOp.forward_native for SiluAndMul and QuantFP8 to avoid raw torch ops inside opaque custom ops (#32806)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

vllm/compilation/matcher_utils.py

@@ -336,6 +336,7 @@ class MatcherQuantFP8(MatcherCustomOp):
             quant_key.scale.group_shape,
             column_major_scales=has_col_major_scales,
             use_ue8m0=is_e8m0,
+            compile_native=False,
         )
 
     def forward_rocm_aiter(