prain: serve with the string chat template content format

2026-11-04 21:50:46 +01:00
parent a67238f66b
commit 1e3a412563
3 changed files with 10 additions and 3 deletions
@@ -55,7 +55,8 @@ class Cli(TmpCase):
        execvp.assert_called_once_with("vllm", [
            "vllm", "serve", "/models/m", "--enforce-eager", "--moe-backend", "triton",
            "--scheduling-policy", "priority", "--max-num-seqs", "3",
-            "--kv-cache-memory-bytes", "1073741824", "--port", "8001"])
+            "--kv-cache-memory-bytes", "1073741824", "--chat-template-content-format", "string",
+            "--port", "8001"])
        with mock.patch("os.execvp") as execvp, self.assertRaisesRegex(
                SystemExit, "--max-num-seqs=4 comes from the placement file"):
            main(["serve", config, "/models/m", "--", "--max-num-seqs=4"])