[Core] Remove tokenizer group in vLLM (#24078)

Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
2025-09-17 01:42:59 -07:00
parent c15309a730
commit 6c47f6bfa4
49 changed files with 276 additions and 934 deletions
--- a/vllm/entrypoints/openai/serving_chat.py
+++ b/vllm/entrypoints/openai/serving_chat.py
@@ -188,7 +188,7 @@ class OpenAIServingChat(OpenAIServing):

            model_name = self.models.model_name(lora_request)

-            tokenizer = await self.engine_client.get_tokenizer(lora_request)
+            tokenizer = await self.engine_client.get_tokenizer()

            tool_parser = self.tool_parser