ling recipe: add --enable-auto-tool-choice --tool-call-parser ling3 (vLLM v0.31.0 Ling3ToolParser) — makes the serve bench-ready for tool scenarios

recipes/ling-31-flash-nvfp4/recipe.toml

@@ -37,6 +37,8 @@ pipeline_parallel_size = 1
 distributed_backend = "mp"
 args = [
     "--served-model-name", "inclusionAI/Ling-3.1-flash",
+    "--enable-auto-tool-choice",
+    "--tool-call-parser", "ling3",
     "--trust-remote-code",
     "--max-model-len", "65536",
     "--gpu-memory-utilization", "0.78",