diff --git a/tests/entrypoints/launchers/test_cli_args.py b/tests/entrypoints/launchers/test_cli_args.py
index 1d98170e55..a9c714ada0 100644
--- a/tests/entrypoints/launchers/test_cli_args.py
+++ b/tests/entrypoints/launchers/test_cli_args.py
@@ -11,6 +11,7 @@ from vllm.entrypoints.launchers.cli_args import (
     validate_parsed_serve_args,
 )
 from vllm.entrypoints.openai.models.protocol import LoRAModulePath
+from vllm.exceptions import VLLMValidationError
 from vllm.utils.argparse_utils import FlexibleArgumentParser
 
 LORA_MODULE = {
@@ -204,7 +205,7 @@ def test_chat_template_validation_for_happy_paths(serve_parser):
 def test_chat_template_validation_for_sad_paths(serve_parser):
     """Ensure validation fails if the chat template doesn't exist"""
     args = serve_parser.parse_args(args=["--chat-template", "does/not/exist"])
-    with pytest.raises(ValueError):
+    with pytest.raises(VLLMValidationError):
         validate_parsed_serve_args(args)
 
 
diff --git a/tests/renderers/test_hf.py b/tests/renderers/test_hf.py
index 24a9e26fe9..c2377e956c 100644
--- a/tests/renderers/test_hf.py
+++ b/tests/renderers/test_hf.py
@@ -6,6 +6,7 @@ import pytest
 from vllm.config import ModelConfig
 from vllm.entrypoints.chat_utils import load_chat_template
 from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
+from vllm.exceptions import VLLMValidationError
 from vllm.renderers.hf import (
     _consolidate_system_messages,
     _convert_developer_to_system,
@@ -97,7 +98,7 @@ def test_no_load_chat_template_filelike():
     # Testing chatml template
     template = "../../examples/does_not_exist"
 
-    with pytest.raises(ValueError, match="looks like a file path"):
+    with pytest.raises(VLLMValidationError, match="looks like a file path"):
         load_chat_template(chat_template=template)
 
 
diff --git a/vllm/entrypoints/chat_utils.py b/vllm/entrypoints/chat_utils.py
index fe0eac85b1..9ff0a04d86 100644
--- a/vllm/entrypoints/chat_utils.py
+++ b/vllm/entrypoints/chat_utils.py
@@ -1446,10 +1446,11 @@ def validate_chat_template(chat_template: Path | str | None):
 
             builtin_template_path = CHAT_TEMPLATES_DIR / chat_template
             if not builtin_template_path.exists():
-                raise ValueError(
+                raise VLLMValidationError(
                     f"The supplied chat template string ({chat_template}) "
                     f"appears path-like, but doesn't exist! "
-                    f"Tried: {chat_template} and {builtin_template_path}"
+                    f"Tried: {chat_template} and {builtin_template_path}",
+                    parameter="chat_template",
                 )
 
     else:
@@ -1497,7 +1498,7 @@ def _load_chat_template(
                     f"Tried: {chat_template} and {builtin_template_path}. "
                     f"Reason: {e}"
                 )
-                raise ValueError(msg) from e
+                raise VLLMValidationError(msg, parameter="chat_template") from e
 
         # If opening a file fails, set chat template to be args to
         # ensure we decode so our escape are interpreted correctly
@@ -1575,7 +1576,8 @@ def _get_full_multimodal_text_prompt(
             logger.debug("Input prompt: %s", text_prompt)
             raise VLLMValidationError(
                 f"Found more '{placeholder}' placeholders in input prompt than "
-                "actual multimodal data items."
+                "actual multimodal data items.",
+                parameter="messages",
             )
 
         missing_placeholders.extend([placeholder] * placeholder_counts[placeholder])
@@ -1833,7 +1835,8 @@ def _reject_reserved_placeholder_in_text(text: str, model_config: ModelConfig) -
         raise VLLMValidationError(
             _RESERVED_PLACEHOLDER_IN_TEXT_ERROR.format(
                 token=PROMPT_EMBEDS_PLACEHOLDER_TOKEN
-            )
+            ),
+            parameter="messages",
         )