fix: add served-model-name with two names to dspark recipe

- --served-model-name deepseek-v4-flash-dspark default

recipes/deepseek-v4-flash-dspark/recipe.toml

@@ -28,6 +28,7 @@ args = [
     "--max-num-batched-tokens", "4096",
     "--max-cudagraph-capture-size", "128",
     "--gpu-memory-utilization", "0.8",
+    "--served-model-name", "deepseek-v4-flash-dspark", "default",
     # Engine backends
     "--attention-backend", "FLASHINFER_MLA_SPARSE_DSV4",
     "--moe-backend", "b12x",