diff --git a/docs/en/llm/api_server_tools.md b/docs/en/llm/api_server_tools.md
index 56fb1b598a..39e91dbf07 100644
--- a/docs/en/llm/api_server_tools.md
+++ b/docs/en/llm/api_server_tools.md
@@ -1,6 +1,6 @@
 # Tools Calling
 
-LMDeploy supports tools for InternLM2, InternLM2.5 and llama3.1 models.
+LMDeploy supports tools for InternLM2, InternLM2.5, llama3.1 and Qwen2.5 models.
 
 ## Single Round Invocation
 
@@ -241,3 +241,156 @@ messages += [
 assistant_response = request_llama3_1_service(messages)
 print(assistant_response)
 ```
+
+### Qwen2.5
+
+Qwen2.5 supports multi tool calling, which means that multiple tool requests can be initiated in one request
+
+```python
+from openai import OpenAI
+import json
+
+def get_current_temperature(location: str, unit: str = "celsius"):
+    """Get current temperature at a location.
+
+    Args:
+        location: The location to get the temperature for, in the format "City, State, Country".
+        unit: The unit to return the temperature in. Defaults to "celsius". (choices: ["celsius", "fahrenheit"])
+
+    Returns:
+        the temperature, the location, and the unit in a dict
+    """
+    return {
+        "temperature": 26.1,
+        "location": location,
+        "unit": unit,
+    }
+
+
+def get_temperature_date(location: str, date: str, unit: str = "celsius"):
+    """Get temperature at a location and date.
+
+    Args:
+        location: The location to get the temperature for, in the format "City, State, Country".
+        date: The date to get the temperature for, in the format "Year-Month-Day".
+        unit: The unit to return the temperature in. Defaults to "celsius". (choices: ["celsius", "fahrenheit"])
+
+    Returns:
+        the temperature, the location, the date and the unit in a dict
+    """
+    return {
+        "temperature": 25.9,
+        "location": location,
+        "date": date,
+        "unit": unit,
+    }
+
+def get_function_by_name(name):
+    if name == "get_current_temperature":
+        return get_current_temperature
+    if name == "get_temperature_date":
+        return get_temperature_date
+
+tools = [{
+    'type': 'function',
+    'function': {
+        'name': 'get_current_temperature',
+        'description': 'Get current temperature at a location.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type': 'string',
+                    'description': 'The location to get the temperature for, in the format \'City, State, Country\'.'
+                },
+                'unit': {
+                    'type': 'string',
+                    'enum': [
+                        'celsius',
+                        'fahrenheit'
+                    ],
+                    'description': 'The unit to return the temperature in. Defaults to \'celsius\'.'
+                }
+            },
+            'required': [
+                'location'
+            ]
+        }
+    }
+}, {
+    'type': 'function',
+    'function': {
+        'name': 'get_temperature_date',
+        'description': 'Get temperature at a location and date.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type': 'string',
+                    'description': 'The location to get the temperature for, in the format \'City, State, Country\'.'
+                },
+                'date': {
+                    'type': 'string',
+                    'description': 'The date to get the temperature for, in the format \'Year-Month-Day\'.'
+                },
+                'unit': {
+                    'type': 'string',
+                    'enum': [
+                        'celsius',
+                        'fahrenheit'
+                    ],
+                    'description': 'The unit to return the temperature in. Defaults to \'celsius\'.'
+                }
+            },
+            'required': [
+                'location',
+                'date'
+            ]
+        }
+    }
+}]
+messages = [{'role': 'user', 'content': 'Today is 2024-11-14, What\'s the temperature in San Francisco now? How about tomorrow?'}]
+
+client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
+model_name = client.models.list().data[0].id
+response = client.chat.completions.create(
+    model=model_name,
+    messages=messages,
+    temperature=0.8,
+    top_p=0.8,
+    stream=False,
+    tools=tools)
+print(response.choices[0].message.tool_calls)
+messages.append(response.choices[0].message)
+
+for tool_call in response.choices[0].message.tool_calls:
+    tool_call_args = json.loads(tool_call.function.arguments)
+    tool_call_result =  get_function_by_name(tool_call.function.name)(**tool_call_args)
+    messages.append({
+        'role': 'tool',
+        'name': tool_call.function.name,
+        'content': tool_call_result,
+        'tool_call_id': tool_call.id
+    })
+
+response = client.chat.completions.create(
+    model=model_name,
+    messages=messages,
+    temperature=0.8,
+    top_p=0.8,
+    stream=False,
+    tools=tools)
+print(response.choices[0].message.content)
+
+```
+
+Using the Qwen2.5-14B-Instruct, similar results can be obtained as follows
+
+```
+[ChatCompletionMessageToolCall(id='0', function=Function(arguments='{"location": "San Francisco, California, USA"}', name='get_current_temperature'), type='function'),
+ ChatCompletionMessageToolCall(id='1', function=Function(arguments='{"location": "San Francisco, California, USA", "date": "2024-11-15"}', name='get_temperature_date'), type='function')]
+
+The current temperature in San Francisco, California, USA is 26.1°C. For tomorrow, 2024-11-15, the temperature is expected to be 25.9°C.
+```
+
+It is important to note that in scenarios involving multiple tool calls, the order of the tool call results can affect the response quality. The tool_call_id has not been correctly provided to the LLM.
diff --git a/docs/zh_cn/llm/api_server_tools.md b/docs/zh_cn/llm/api_server_tools.md
index 643a39d5d2..8688ea35cd 100644
--- a/docs/zh_cn/llm/api_server_tools.md
+++ b/docs/zh_cn/llm/api_server_tools.md
@@ -1,6 +1,6 @@
 # Tools
 
-LMDeploy 支持 InternLM2, InternLM2.5 和 Llama3.1 模型的工具调用。
+LMDeploy 支持 InternLM2, InternLM2.5, Llama3.1 和 Qwen2.5模型的工具调用。
 
 ## 单轮调用
 
@@ -241,3 +241,156 @@ messages += [
 assistant_response = request_llama3_1_service(messages)
 print(assistant_response)
 ```
+
+### Qwen2.5
+
+Qwen2.5 支持了多工具调用，这意味着可以在一次请求中可能发起多个工具请求
+
+```python
+from openai import OpenAI
+import json
+
+def get_current_temperature(location: str, unit: str = "celsius"):
+    """Get current temperature at a location.
+
+    Args:
+        location: The location to get the temperature for, in the format "City, State, Country".
+        unit: The unit to return the temperature in. Defaults to "celsius". (choices: ["celsius", "fahrenheit"])
+
+    Returns:
+        the temperature, the location, and the unit in a dict
+    """
+    return {
+        "temperature": 26.1,
+        "location": location,
+        "unit": unit,
+    }
+
+
+def get_temperature_date(location: str, date: str, unit: str = "celsius"):
+    """Get temperature at a location and date.
+
+    Args:
+        location: The location to get the temperature for, in the format "City, State, Country".
+        date: The date to get the temperature for, in the format "Year-Month-Day".
+        unit: The unit to return the temperature in. Defaults to "celsius". (choices: ["celsius", "fahrenheit"])
+
+    Returns:
+        the temperature, the location, the date and the unit in a dict
+    """
+    return {
+        "temperature": 25.9,
+        "location": location,
+        "date": date,
+        "unit": unit,
+    }
+
+def get_function_by_name(name):
+    if name == "get_current_temperature":
+        return get_current_temperature
+    if name == "get_temperature_date":
+        return get_temperature_date
+
+tools = [{
+    'type': 'function',
+    'function': {
+        'name': 'get_current_temperature',
+        'description': 'Get current temperature at a location.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type': 'string',
+                    'description': 'The location to get the temperature for, in the format \'City, State, Country\'.'
+                },
+                'unit': {
+                    'type': 'string',
+                    'enum': [
+                        'celsius',
+                        'fahrenheit'
+                    ],
+                    'description': 'The unit to return the temperature in. Defaults to \'celsius\'.'
+                }
+            },
+            'required': [
+                'location'
+            ]
+        }
+    }
+}, {
+    'type': 'function',
+    'function': {
+        'name': 'get_temperature_date',
+        'description': 'Get temperature at a location and date.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type': 'string',
+                    'description': 'The location to get the temperature for, in the format \'City, State, Country\'.'
+                },
+                'date': {
+                    'type': 'string',
+                    'description': 'The date to get the temperature for, in the format \'Year-Month-Day\'.'
+                },
+                'unit': {
+                    'type': 'string',
+                    'enum': [
+                        'celsius',
+                        'fahrenheit'
+                    ],
+                    'description': 'The unit to return the temperature in. Defaults to \'celsius\'.'
+                }
+            },
+            'required': [
+                'location',
+                'date'
+            ]
+        }
+    }
+}]
+messages = [{'role': 'user', 'content': 'Today is 2024-11-14, What\'s the temperature in San Francisco now? How about tomorrow?'}]
+
+client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
+model_name = client.models.list().data[0].id
+response = client.chat.completions.create(
+    model=model_name,
+    messages=messages,
+    temperature=0.8,
+    top_p=0.8,
+    stream=False,
+    tools=tools)
+print(response.choices[0].message.tool_calls)
+messages.append(response.choices[0].message)
+
+for tool_call in response.choices[0].message.tool_calls:
+    tool_call_args = json.loads(tool_call.function.arguments)
+    tool_call_result =  get_function_by_name(tool_call.function.name)(**tool_call_args)
+    messages.append({
+        'role': 'tool',
+        'name': tool_call.function.name,
+        'content': tool_call_result,
+        'tool_call_id': tool_call.id
+    })
+
+response = client.chat.completions.create(
+    model=model_name,
+    messages=messages,
+    temperature=0.8,
+    top_p=0.8,
+    stream=False,
+    tools=tools)
+print(response.choices[0].message.content)
+
+```
+
+使用Qwen2.5-14B-Instruct，可以得到以下类似结果
+
+```
+[ChatCompletionMessageToolCall(id='0', function=Function(arguments='{"location": "San Francisco, California, USA"}', name='get_current_temperature'), type='function'),
+ ChatCompletionMessageToolCall(id='1', function=Function(arguments='{"location": "San Francisco, California, USA", "date": "2024-11-15"}', name='get_temperature_date'), type='function')]
+
+The current temperature in San Francisco, California, USA is 26.1°C. For tomorrow, 2024-11-15, the temperature is expected to be 25.9°C.
+```
+
+需要注意的是，多工具调用的情况下，工具调用的结果顺序会影响回答的效果，tool_call_id并没有正确给到LLM.
diff --git a/lmdeploy/model.py b/lmdeploy/model.py
index 2b3a0a4e1d..b699fe4242 100644
--- a/lmdeploy/model.py
+++ b/lmdeploy/model.py
@@ -927,7 +927,8 @@ def match(cls, model_path: str) -> Optional[str]:
         Args:
             model_path (str): the model path used for matching.
         """
-        if 'qwen' in model_path.lower():
+        if 'qwen' in model_path.lower() and 'qwen2.5' not in model_path.lower(
+        ):
             return 'qwen'
         if 'minicpm-v-2_6' in model_path.lower():
             return 'minicpmv-2d6'
@@ -935,6 +936,113 @@ def match(cls, model_path: str) -> Optional[str]:
             return 'minicpm3'
 
 
+@MODELS.register_module(name='qwen2d5')
+class Qwen2d5Chat(Qwen7BChat):
+    """Chat template for Qwen2.5-Instruct series."""
+
+    def __init__(
+            self,
+            system='<|im_start|>system\n',
+            meta_instruction='You are Qwen, created by Alibaba Cloud. You are a helpful assistant.',
+            eosys='<|im_end|>\n',
+            user='<|im_start|>user\n',
+            eoh='<|im_end|>\n',
+            assistant='<|im_start|>assistant\n',
+            eoa='<|im_end|>',
+            separator='\n',
+            tools="""\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>""",
+            eotools="""\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{"name": <function-name>, "arguments": <args-json-object>}\n</tool_call>""",
+            stop_words=['<|im_end|>'],
+            **kwargs):
+
+        self.tools = tools
+        self.eotools = eotools
+        super().__init__(system=system,
+                         meta_instruction=meta_instruction,
+                         eosys=eosys,
+                         user=user,
+                         eoh=eoh,
+                         assistant=assistant,
+                         eoa=eoa,
+                         separator=separator,
+                         stop_words=stop_words,
+                         **kwargs)
+
+    def messages2prompt(self,
+                        messages,
+                        sequence_start=True,
+                        tools=None,
+                        **kwargs):
+        """Return the prompt that is concatenated with other elements in the
+        chat template.
+
+        Args:
+            messages (str | List): user's input prompt
+        Returns:
+            str: the concatenated prompt
+        """
+        if isinstance(messages, str):
+            return self.get_prompt(messages, sequence_start)
+        box_map = dict(user=self.user,
+                       assistant=self.assistant,
+                       system=self.system)
+        ret = ''
+        tool_prompt = ''
+        if tools is not None and len(tools) > 0:
+            for tool in tools:
+                tool_prompt += self.separator
+                tool_prompt += f'{{"type": "function", "function": {json.dumps(tool, ensure_ascii=False)}}}'
+            if len(messages) and messages[0]['role'] == 'system':
+                ret += f"{self.system}{messages[0]['content']}{self.tools}{tool_prompt}{self.eotools}{self.eosys}"
+            else:
+                ret += f'{self.system}{self.meta_instruction}{self.tools}{tool_prompt}{self.eotools}{self.eosys}'
+        else:
+            if self.meta_instruction is not None and sequence_start:
+                if len(messages) and messages[0]['role'] == 'system':
+                    ret += f"{self.system}{messages[0]['content']}{self.eosys}"
+                else:
+                    ret += f'{self.system}{self.meta_instruction}{self.eosys}'
+
+        for index, message in enumerate(messages):
+            if (message['role'] == 'user'
+                    or (message['role'] == 'system' and index != 0)
+                    or (message['role'] == 'assistant'
+                        and message.get('tool_calls') is None)):
+                ret += f"{box_map[message['role']]}{message['content']}{self.eosys}"
+            elif message['role'] == 'assistant':
+                ret += f'<|im_start|>assistant'
+                if message.get('content') is not None:
+                    ret += f"{self.separator}{message['content']}"
+
+                if message.get('tool_calls') is not None:
+                    tool_calls = message['tool_calls']
+                    for tool_call in tool_calls:
+                        if tool_call.get('function') is not None:
+                            tool_call = tool_call['function']
+                        ret += f'{self.separator}<tool_call>{self.separator}{{"name": "{tool_call["name"]}", "arguments": {json.dumps(tool_call["arguments"], ensure_ascii=False)}}}{self.separator}</tool_call>'
+                ret += self.eosys
+            if message['role'] == 'tool':
+                if index == 0 or messages[index - 1]['role'] != 'tool':
+                    ret += f'<|im_start|>user'
+                ret += f"{self.separator}<tool_response>{self.separator}{message['content']}{self.separator}</tool_response>"
+                if index == len(messages) - 1 or messages[index +
+                                                          1]['role'] != 'tool':
+                    ret += f'{self.eoh}'
+        ret += f'{self.assistant}'
+        return ret
+
+    @classmethod
+    def match(cls, model_path: str) -> Optional[str]:
+        """Return the model_name that was registered to MODELS.
+
+        Args:
+            model_path (str): the model path used for matching.
+        """
+        lower_path = model_path.lower()
+        if 'qwen2.5' in lower_path or 'qwen2_5' in lower_path:
+            return 'qwen2d5'
+
+
 @MODELS.register_module(name='codellama')
 class CodeLlama(Llama2):
 
diff --git a/lmdeploy/serve/async_engine.py b/lmdeploy/serve/async_engine.py
index 3c8f193cd5..f3c3432328 100644
--- a/lmdeploy/serve/async_engine.py
+++ b/lmdeploy/serve/async_engine.py
@@ -4,6 +4,7 @@
 import json
 import os
 import random
+import re
 from contextlib import asynccontextmanager
 from copy import deepcopy
 from itertools import count
@@ -648,14 +649,37 @@ def parse_tool_response(self, text, tools, **kwargs):
             name, parameters = action['name'], json.dumps(action.get(
                 'parameters', action.get('arguments', {})),
                                                           ensure_ascii=False)
+            call_info_list = [(name, parameters)]
         elif '<function=' in text:  # llama3.1
             action, _ = text.split('</function>')
             parameters = action[action.find('{'):]
             name = action.split('<function=')[1].split('>{')[0]
+            call_info_list = [(name, parameters)]
+        elif '<tool_call>' in text and '</tool_call>' in text:  # qwen2.5
+            # get tool_call in text
+            pattern = r'<tool_call>(.*?)</tool_call>'
+            match_result_list = re.findall(pattern, text, re.DOTALL)
+            call_info_list = []
+            for match_result in match_result_list:
+                action = json.loads(match_result)
+                call_info_list.append((action['name'],
+                                       json.dumps(action['arguments'],
+                                                  ensure_ascii=False)))
+            # get text outside of tags
+            if not text.startswith('<tool_call>'):
+                text = text[:text.find('<tool_call>')]
+            elif not text.endswith('</tool_call>'):
+                text = text[text.rfind('</tool_call>') + len('</tool_call>'):]
+            else:
+                text = ''
+
         else:
             raise RuntimeError(f'Unexpected model response: {text}')
-        action_id = [tool.function.name for tool in tools].index(name)
-        return text, action_id, name, parameters
+
+        call_info_list = [([tool.function.name for tool in tools
+                            ].index(call_info[0]), call_info[0], call_info[1])
+                          for call_info in call_info_list]
+        return text, call_info_list
 
     def chat(self,
              prompt: str,
diff --git a/lmdeploy/serve/openai/api_server.py b/lmdeploy/serve/openai/api_server.py
index a12cadaa7d..2d0560720d 100644
--- a/lmdeploy/serve/openai/api_server.py
+++ b/lmdeploy/serve/openai/api_server.py
@@ -495,17 +495,18 @@ async def completion_stream_generator() -> AsyncGenerator[str, None]:
             final_logprobs.extend(res.logprobs)
 
     tool_calls = None
-    if request.tool_choice != 'none' and ('<|plugin|>' in text
-                                          or '<function=' in text):
+    if request.tool_choice != 'none' and ('<|plugin|>' in text or '<function='
+                                          in text or '<tool_call>' in text):
         if final_res.finish_reason == 'stop':
             final_res.finish_reason = 'tool_calls'
         try:  # TODO add json_schema guidance to turbomind
-            text, action_id, name, parameters = VariableInterface.async_engine.parse_tool_response(  # noqa
+            text, call_info_list = VariableInterface.async_engine.parse_tool_response(  # noqa
                 text, request.tools)
             tool_calls = [
-                ToolCall(id=str(action_id),
-                         function=FunctionResponse(name=name,
-                                                   arguments=parameters))
+                ToolCall(id=str(call_info[0]),
+                         function=FunctionResponse(name=call_info[1],
+                                                   arguments=call_info[2]))
+                for call_info in call_info_list
             ]
         except Exception as e:
             logger.error(f'Exception: {e}')
diff --git a/tests/test_lmdeploy/test_model.py b/tests/test_lmdeploy/test_model.py
index a38971e4d0..ae21053308 100644
--- a/tests/test_lmdeploy/test_model.py
+++ b/tests/test_lmdeploy/test_model.py
@@ -9,6 +9,7 @@
      ('internlm/internlm2-1_8b', ['base']),
      ('models--internlm--internlm-chat-7b/snapshots/1234567', ['internlm']),
      ('Qwen/Qwen-7B-Chat', ['qwen']),
+     ('Qwen/Qwen2.5-7B-Instruct', ['qwen2d5']),
      ('codellama/CodeLlama-7b-hf', ['codellama']),
      ('upstage/SOLAR-0-70b', ['solar', 'solar-70b']),
      ('meta-llama/Llama-2-7b-chat-hf', ['llama2']),
@@ -283,6 +284,291 @@ def test_qwen():
         assert _prompt is None
 
 
+def test_qwen2d5():
+    prompt = 'hello, can u introduce yourself'
+    model = MODELS.get('qwen2d5')(capability='completion')
+    assert model.get_prompt(prompt, sequence_start=True) == prompt
+    assert model.get_prompt(prompt, sequence_start=False) == prompt
+
+    model = MODELS.get('qwen2d5')(capability='chat')
+
+    # No tool call
+    messages = [
+        dict(role='user',
+             content='What\'s the temperature in San Francisco now?')
+    ]
+    no_tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                      'Cloud. You are a helpful '
+                      "assistant.<|im_end|>\n<|im_start|>user\nWhat's the "
+                      'temperature in San Francisco '
+                      'now?<|im_end|>\n<|im_start|>assistant\n')
+    assert model.messages2prompt(messages) == no_tool_prompt
+    assert model.messages2prompt(messages, tools=[]) == no_tool_prompt
+
+    messages.append({'role': 'assistant', 'content': 'I don\'t know.'})
+    no_tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                      'Cloud. You are a helpful '
+                      "assistant.<|im_end|>\n<|im_start|>user\nWhat's the "
+                      'temperature in San Francisco '
+                      "now?<|im_end|>\n<|im_start|>assistant\nI don't "
+                      'know.<|im_end|>\n<|im_start|>assistant\n')
+    assert model.messages2prompt(messages) == no_tool_prompt
+    # Single tool call
+    tools = [{
+        'name': 'get_current_temperature',
+        'description': 'Get current temperature at a location.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type':
+                    'string',
+                    'description':
+                    'The location to get the temperature for,'
+                    ' in the format \'City, State, Country\'.'
+                },
+                'unit': {
+                    'type':
+                    'string',
+                    'enum': ['celsius', 'fahrenheit'],
+                    'description':
+                    'The unit to return the temperature in. Defaults to '
+                    '\'celsius\'.'
+                }
+            },
+            'required': ['location']
+        }
+    }]
+
+    messages = [
+        dict(role='user',
+             content='What\'s the temperature in San Francisco now?')
+    ]
+    tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                   'Cloud. You are a helpful assistant.\n\n# Tools\n\nYou '
+                   'may call one or more functions to assist with the user '
+                   'query.\n\nYou are provided with function signatures '
+                   "within <tools></tools> XML tags:\n<tools>\n{\"type\": "
+                   "\"function\", \"function\": {\"name\": "
+                   "\"get_current_temperature\", \"description\": \"Get "
+                   "current temperature at a location.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"unit\": {\"type\": \"string\", \"enum\": "
+                   "[\"celsius\", \"fahrenheit\"], \"description\": \"The "
+                   'unit to return the temperature in. Defaults to '
+                   "'celsius'.\"}}, \"required\": ["
+                   "\"location\"]}}}\n</tools>\n\nFor each function call, "
+                   'return a json object with function name and arguments '
+                   'within <tool_call></tool_call> XML tags:\n<tool_call>\n{'
+                   "\"name\": <function-name>, \"arguments\": "
+                   '<args-json-object>}\n</tool_call><|im_end|>\n<|im_start'
+                   "|>user\nWhat's the temperature in San Francisco "
+                   'now?<|im_end|>\n<|im_start|>assistant\n')
+    assert model.messages2prompt(messages, tools=tools) == tool_prompt
+
+    messages.append(
+        dict(role='tool',
+             name='get_current_temperature',
+             content={
+                 'temperature': 26.1,
+                 'location': 'San Francisco, California, USA',
+                 'unit': 'celsius'
+             },
+             tool_call_id='0'))
+    tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                   'Cloud. You are a helpful assistant.\n\n# Tools\n\nYou '
+                   'may call one or more functions to assist with the user '
+                   'query.\n\nYou are provided with function signatures '
+                   "within <tools></tools> XML tags:\n<tools>\n{\"type\": "
+                   "\"function\", \"function\": {\"name\": "
+                   "\"get_current_temperature\", \"description\": \"Get "
+                   "current temperature at a location.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"unit\": {\"type\": \"string\", \"enum\": "
+                   "[\"celsius\", \"fahrenheit\"], \"description\": \"The "
+                   'unit to return the temperature in. Defaults to '
+                   "'celsius'.\"}}, \"required\": ["
+                   "\"location\"]}}}\n</tools>\n\nFor each function call, "
+                   'return a json object with function name and arguments '
+                   'within <tool_call></tool_call> XML tags:\n<tool_call>\n{'
+                   "\"name\": <function-name>, \"arguments\": "
+                   '<args-json-object>}\n</tool_call><|im_end|>\n<|im_start'
+                   "|>user\nWhat's the temperature in San Francisco "
+                   'now?<|im_end|>\n<|im_start|>user\n<tool_response>\n{'
+                   "'temperature': 26.1, 'location': 'San Francisco, "
+                   "California, USA', 'unit': "
+                   "'celsius'}\n</tool_response><|im_end|>\n<|im_start"
+                   '|>assistant\n')
+    assert model.messages2prompt(messages, tools=tools) == tool_prompt
+    # Multi tool calling
+    tools = [{
+        'name': 'get_current_temperature',
+        'description': 'Get current temperature at a location.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type':
+                    'string',
+                    'description':
+                    'The location to get the temperature for, in the format '
+                    '\'City, State, Country\'.'
+                },
+                'unit': {
+                    'type':
+                    'string',
+                    'enum': ['celsius', 'fahrenheit'],
+                    'description':
+                    'The unit to return the temperature in.'
+                    ' Defaults to \'celsius\'.'
+                }
+            },
+            'required': ['location']
+        }
+    }, {
+        'name': 'get_temperature_date',
+        'description': 'Get temperature at a location and date.',
+        'parameters': {
+            'type': 'object',
+            'properties': {
+                'location': {
+                    'type':
+                    'string',
+                    'description':
+                    'The location to get the temperature for,'
+                    ' in the format \'City, State, Country\'.'
+                },
+                'date': {
+                    'type':
+                    'string',
+                    'description':
+                    'The date to get the temperature for,'
+                    ' in the format \'Year-Month-Day\'.'
+                },
+                'unit': {
+                    'type':
+                    'string',
+                    'enum': ['celsius', 'fahrenheit'],
+                    'description':
+                    'The unit to return the temperature in.'
+                    ' Defaults to \'celsius\'.'
+                }
+            },
+            'required': ['location', 'date']
+        }
+    }]
+    messages = [
+        dict(role='user',
+             content='Today is 2024-11-14, What\'s the temperature in'
+             ' San Francisco now? How about tomorrow?')
+    ]
+    tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                   'Cloud. You are a helpful assistant.\n\n# Tools\n\nYou '
+                   'may call one or more functions to assist with the user '
+                   'query.\n\nYou are provided with function signatures '
+                   "within <tools></tools> XML tags:\n<tools>\n{\"type\": "
+                   "\"function\", \"function\": {\"name\": "
+                   "\"get_current_temperature\", \"description\": \"Get "
+                   "current temperature at a location.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"unit\": {\"type\": \"string\", \"enum\": "
+                   "[\"celsius\", \"fahrenheit\"], \"description\": \"The "
+                   'unit to return the temperature in. Defaults to '
+                   "'celsius'.\"}}, \"required\": [\"location\"]}}}\n{"
+                   "\"type\": \"function\", \"function\": {\"name\": "
+                   "\"get_temperature_date\", \"description\": \"Get "
+                   "temperature at a location and date.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"date\": {\"type\": \"string\", "
+                   "\"description\": \"The date to get the temperature for, "
+                   "in the format 'Year-Month-Day'.\"}, \"unit\": {\"type\": "
+                   "\"string\", \"enum\": [\"celsius\", \"fahrenheit\"], "
+                   "\"description\": \"The unit to return the temperature "
+                   "in. Defaults to 'celsius'.\"}}, \"required\": ["
+                   "\"location\", \"date\"]}}}\n</tools>\n\nFor each "
+                   'function call, return a json object with function name '
+                   'and arguments within <tool_call></tool_call> XML '
+                   "tags:\n<tool_call>\n{\"name\": <function-name>, "
+                   "\"arguments\": "
+                   '<args-json-object>}\n</tool_call><|im_end|>\n<|im_start'
+                   "|>user\nToday is 2024-11-14, What's the temperature in "
+                   'San Francisco now? How about '
+                   'tomorrow?<|im_end|>\n<|im_start|>assistant\n')
+    assert model.messages2prompt(messages, tools=tools) == tool_prompt
+
+    messages.append(
+        dict(role='tool',
+             name='get_current_temperature',
+             content={
+                 'temperature': 26.1,
+                 'location': 'San Francisco, California, USA',
+                 'unit': 'celsius'
+             },
+             tool_call_id='0'))
+    messages.append(
+        dict(role='tool',
+             name='get_temperature_date',
+             content={
+                 'temperature': 25.9,
+                 'location': 'San Francisco, California, USA',
+                 'date': '2024-11-15',
+                 'unit': 'celsius'
+             },
+             tool_call_id='1'))
+    tool_prompt = ('<|im_start|>system\nYou are Qwen, created by Alibaba '
+                   'Cloud. You are a helpful assistant.\n\n# Tools\n\nYou '
+                   'may call one or more functions to assist with the user '
+                   'query.\n\nYou are provided with function signatures '
+                   "within <tools></tools> XML tags:\n<tools>\n{\"type\": "
+                   "\"function\", \"function\": {\"name\": "
+                   "\"get_current_temperature\", \"description\": \"Get "
+                   "current temperature at a location.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"unit\": {\"type\": \"string\", \"enum\": "
+                   "[\"celsius\", \"fahrenheit\"], \"description\": \"The "
+                   'unit to return the temperature in. Defaults to '
+                   "'celsius'.\"}}, \"required\": [\"location\"]}}}\n{"
+                   "\"type\": \"function\", \"function\": {\"name\": "
+                   "\"get_temperature_date\", \"description\": \"Get "
+                   "temperature at a location and date.\", \"parameters\": {"
+                   "\"type\": \"object\", \"properties\": {\"location\": {"
+                   "\"type\": \"string\", \"description\": \"The location to "
+                   "get the temperature for, in the format 'City, State, "
+                   "Country'.\"}, \"date\": {\"type\": \"string\", "
+                   "\"description\": \"The date to get the temperature for, "
+                   "in the format 'Year-Month-Day'.\"}, \"unit\": {\"type\": "
+                   "\"string\", \"enum\": [\"celsius\", \"fahrenheit\"], "
+                   "\"description\": \"The unit to return the temperature "
+                   "in. Defaults to 'celsius'.\"}}, \"required\": ["
+                   "\"location\", \"date\"]}}}\n</tools>\n\nFor each "
+                   'function call, return a json object with function name '
+                   'and arguments within <tool_call></tool_call> XML '
+                   "tags:\n<tool_call>\n{\"name\": <function-name>, "
+                   "\"arguments\": "
+                   '<args-json-object>}\n</tool_call><|im_end|>\n<|im_start'
+                   "|>user\nToday is 2024-11-14, What's the temperature in "
+                   'San Francisco now? How about '
+                   'tomorrow?<|im_end|>\n<|im_start|>user\n<tool_response'
+                   ">\n{'temperature': 26.1, 'location': 'San Francisco, "
+                   "California, USA', 'unit': "
+                   "'celsius'}\n</tool_response>\n<tool_response>\n{"
+                   "'temperature': 25.9, 'location': 'San Francisco, "
+                   "California, USA', 'date': '2024-11-15', 'unit': "
+                   "'celsius'}\n</tool_response><|im_end|>\n<|im_start"
+                   '|>assistant\n')
+    assert model.messages2prompt(messages, tools=tools) == tool_prompt
+
+
 def test_codellama_completion():
     model = MODELS.get('codellama')(capability='completion')
     prompt = """\