[V1] v1 engine + full CUDA graph support for PLaMo2 (#23998)

Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
Co-authored-by: Hemmi Shinichi <shemmi@preferred.jp>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>

vllm/config/compilation.py

@@ -340,6 +340,7 @@ class CompilationConfig:
         "vllm.mamba_mixer",
         "vllm.short_conv",
         "vllm.linear_attention",
+        "vllm.plamo2_mamba_mixer",
     ]
 
     def compute_hash(self) -> str: