fix(frontend): return HTTP 400 for out-of-vocabulary token_ids_logprob (#28088)

Signed-off-by: Ting Sun <suntcrick@gmail.com>

python/sglang/srt/managers/tokenizer_manager.py

@@ -985,8 +985,9 @@ class TokenizerManager(TokenizerControlMixin, TokenizerManagerScoreMixin):
         if isinstance(obj, EmbeddingReqInput):
             self._validate_for_matryoshka_dim(obj)
 
-        # Validate custom logit processor
+        # Validate generation-specific fields
         if isinstance(obj, GenerateReqInput):
+            self._validate_token_ids_logprob(obj)
             if (
                 obj.return_hidden_states
                 and not self.server_args.enable_return_hidden_states
@@ -1047,6 +1048,26 @@ class TokenizerManager(TokenizerControlMixin, TokenizerManagerScoreMixin):
                 f"Provided dimensions are greater than max embedding dimension: {self.model_config.hidden_size}"
             )
 
+    def _validate_token_ids_logprob(self, obj: GenerateReqInput) -> None:
+        # Batch requests are split into per-request sub-objects before this
+        # runs (normalize_batch_and_arguments + __getitem__), so the only
+        # legal shape here is the per-request contract of
+        # TokenizedGenerateReqInput.token_ids_logprob: a flat list of ints.
+        token_ids_logprob = obj.token_ids_logprob
+        if not token_ids_logprob:
+            return
+        if not isinstance(token_ids_logprob, list):
+            raise ValueError("token_ids_logprob must be a flat list of integers.")
+        vocab_size = self.model_config.vocab_size
+        for token_id in token_ids_logprob:
+            if not isinstance(token_id, int):
+                raise ValueError("token_ids_logprob must be a flat list of integers.")
+            if token_id < 0 or token_id >= vocab_size:
+                raise ValueError(
+                    f"token_ids_logprob contains out-of-vocabulary token id "
+                    f"{token_id}; valid range is [0, {vocab_size})."
+                )
+
     def _validate_input_ids_in_vocab(
         self, input_ids: Union[List[int], List[List[int]]], vocab_size: int
     ) -> None: