From 96c52766c64bbc6feb2655e5471c85b758754bb0 Mon Sep 17 00:00:00 2001
From: jiant <107457950+JadoTu@users.noreply.github.com>
Date: Thu, 27 Nov 2025 07:07:16 +0000
Subject: [PATCH 1/2] feat: add eos_token_id in generation_config to
 SamplingParams._stop_word_ids

Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
---
 tensorrt_llm/sampling_params.py | 40 ++++++++++++++-------------------
 1 file changed, 17 insertions(+), 23 deletions(-)

diff --git a/tensorrt_llm/sampling_params.py b/tensorrt_llm/sampling_params.py
index c9d6e1f44b2c..97fb399055ac 100644
--- a/tensorrt_llm/sampling_params.py
+++ b/tensorrt_llm/sampling_params.py
@@ -368,14 +368,6 @@ def _setup(
         if self.end_id is None:
             self.end_id = tokenizer.eos_token_id
             self.pad_id = tokenizer.pad_token_id
-            # kimi_k2 model uses the eos_token_id in generation config
-            if (
-                hf_model_config is not None
-                and hf_model_config.model_type == "kimi_k2"
-                and generation_config is not None
-                and isinstance(generation_config.eos_token_id, int)
-            ):
-                self.end_id = generation_config.eos_token_id
 
             if self.pad_id is None:
                 self.pad_id = self.end_id
@@ -395,24 +387,26 @@ def _encode(tokenizer, text, add_special_tokens):
             strs = [self.stop] if isinstance(self.stop, str) else self.stop
             self._stop_word_ids = [_encode(tokenizer, s, add_special_tokens) for s in strs]
 
-        # add generation_config to stop word list, only in qwen3-next now
-        if (
-            hf_model_config is not None
-            and hf_model_config.model_type == "qwen3_next"
-            and generation_config is not None
-            and isinstance(generation_config.eos_token_id, List)
-            and all(isinstance(i, int) for i in generation_config.eos_token_id)
-        ):
-            if self._stop_word_ids:
+        # Add eos_token_id in generation_config to _stop_word_ids
+        # Refer to https://huggingface.co/docs/hub/en/transformers#transformers-repository-files and
+        # https://github.com/huggingface/transformers/blob/1ae4d917ed3badbdb1ffc167e0529f5a6d3c080d/src/transformers/generation/stopping_criteria.py#L451C1-L451C42
+        # The eos_token_id in generation_config are really mean to stop the text generation.
+        if generation_config is not None and generation_config.eos_token_id is not None:
+            if isinstance(generation_config.eos_token_id, int):
+                generation_eos_token_ids = [generation_config.eos_token_id]
+            else:  # always List[int]
+                generation_eos_token_ids = generation_config.eos_token_id
+
+            if self._stop_word_ids is None:
+                self._stop_word_ids = [generation_eos_token_ids]
+            else:
                 all_stop_tokens_id = set(i for sublist in self._stop_word_ids for i in sublist)
-                from_generation_stop_tokens = [
-                    i for i in generation_config.eos_token_id if i not in all_stop_tokens_id
+                from_generation_stop_token_ids = [
+                    i for i in generation_eos_token_ids if i not in all_stop_tokens_id
                 ]
 
-                if from_generation_stop_tokens:
-                    self._stop_word_ids.append(from_generation_stop_tokens)
-            else:
-                self._stop_word_ids = [generation_config.eos_token_id]
+                if from_generation_stop_token_ids:
+                    self._stop_word_ids.append(from_generation_stop_token_ids)
 
         return self
 

From 3b619dae4a3e85dcb3d07c049460a12ece05bc7c Mon Sep 17 00:00:00 2001
From: jiant <107457950+JadoTu@users.noreply.github.com>
Date: Tue, 9 Dec 2025 16:04:55 +0000
Subject: [PATCH 2/2] change prompt of failed test

Signed-off-by: jiant <107457950+JadoTu@users.noreply.github.com>
---
 tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py b/tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py
index d287e5e35eb5..c7a4fc7f1644 100644
--- a/tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py
+++ b/tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py
@@ -110,7 +110,7 @@ async def test_chat_completion_top1_logprobs(async_client: openai.AsyncOpenAI,
         "content": "You are a helpful assistant."
     }, {
         "role": "user",
-        "content": "What is the capital of France?"
+        "content": "What is the capital of France? please in detail."
     }]
     # Test top_logprobs=1
     chat_completion = await async_client.chat.completions.create(