feat(frontend): early-fail tokenization guard for user requests (#31366)

Signed-off-by: limingliang <limingliang@stepfun.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: limingliang <limingliang@stepfun.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/tokenizers/deepseek_v32.py

@@ -115,6 +115,10 @@ class DeepseekV32Tokenizer(CachedHfTokenizer):
     def max_token_id(self) -> int:
         return self.tokenizer.max_token_id
 
+    @property
+    def max_chars_per_token(self) -> int:
+        return self.tokenizer.max_chars_per_token
+
     @property
     def truncation_side(self) -> str:
         return self.tokenizer.truncation_side