Skip to content

[Bug] Tool calling is broken for Deepseek models #8580

@pyc96

Description

@pyc96

Checklist

  • 1. I have searched related issues but cannot get the expected help.
  • 2. The bug has not been fixed in the latest version.
  • 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
  • 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
  • 5. Please use English, otherwise it will be closed.

Describe the bug

#6556 updated how tools are formatted and it doesn't work with Deepseek models.

Deepseek jinja template expects the tools are instances of tool.function, but after that PR they are tool

Updating deepseek jinja template

 {% set tool_ns.text = tool_ns.text + '- `' + tool['name'] + '`:\n```json\n' + (tool | tojson) + '\n```\n' %}

to

 {% set tool_ns.text = tool_ns.text + '- `' + tool['function']['name'] + '`:\n```json\n' + (tool | tojson) + '\n```\n' %}

seems to fix the issue, but I am not sure this is the proper fix. Another option is if we can fix or revert #6556

Reproduction

Launch a deepseek model with FC

python -m sglang.launch_server --port=7080  --model=deepseek-ai/DeepSeek-R1-0528  --trust-remote-code --tp=8 --tool-call-parser=deepseekv3 --chat-template=/sgl-workspace/sglang/examples/chat_template/tool_chat_template_deepseekr1.jinja

[2025-07-30 10:53:31] Error in request: 'dict object' has no attribute 'name'
Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/openai/serving_chat.py", line 217, in _apply_jinja_template
    prompt_ids = self.tokenizer_manager.tokenizer.apply_chat_template(
  File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 1641, in apply_chat_template
    rendered_chat, generation_indices = render_jinja_template(
  File "/usr/local/lib/python3.10/dist-packages/transformers/utils/chat_template_utils.py", line 507, in render_jinja_template
    rendered_chat = compiled_template.render(
  File "/usr/local/lib/python3.10/dist-packages/jinja2/environment.py", line 1295, in render
    self.environment.handle_exception()
  File "/usr/local/lib/python3.10/dist-packages/jinja2/environment.py", line 942, in handle_exception
    raise rewrite_traceback_stack(source=source)
  File "<template>", line 39, in top-level template code
jinja2.exceptions.UndefinedError: 'dict object' has no attribute 'name'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/openai/serving_base.py", line 35, in handle_request
    adapted_request, processed_request = self._convert_to_internal_request(
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/openai/serving_chat.py", line 80, in _convert_to_internal_request
    processed_messages = self._process_messages(request, is_multimodal)
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/openai/serving_chat.py", line 143, in _process_messages
    result = self._apply_jinja_template(request, tools, is_multimodal)
  File "/sgl-workspace/sglang/python/sglang/srt/entrypoints/openai/serving_chat.py", line 236, in _apply_jinja_template
    prompt_ids = self.tokenizer_manager.tokenizer.apply_chat_template(
  File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 1641, in apply_chat_template
    rendered_chat, generation_indices = render_jinja_template(
  File "/usr/local/lib/python3.10/dist-packages/transformers/utils/chat_template_utils.py", line 507, in render_jinja_template
    rendered_chat = compiled_template.render(
  File "/usr/local/lib/python3.10/dist-packages/jinja2/environment.py", line 1295, in render
    self.environment.handle_exception()
  File "/usr/local/lib/python3.10/dist-packages/jinja2/environment.py", line 942, in handle_exception
    raise rewrite_traceback_stack(source=source)
  File "<template>", line 39, in top-level template code
curl -X POST -H "Content-Type: application/json" http://localhost:7080/v1/chat/completions -d '{
  "model": "deepseek-ai/DeepSeek-R1-0528-FP4",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather like in Boston today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location", "unit"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'
{"object":"error","message":"Internal server error: 'dict object' has no attribute 'name'","type":"InternalServerError","param":null,"code":500}r

Environment

python3 -m sglang.check_env
Python: 3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA B200
GPU 0,1,2,3,4,5,6,7 Compute Capability: 10.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.8, V12.8.93
CUDA Driver Version: 570.133.20
PyTorch: 2.7.1+cu128
sglang: 0.4.9.post4
sgl_kernel: 0.2.7
flashinfer_python: 0.2.9rc1
triton: 3.3.1
transformers: 4.53.2
torchao: 0.9.0
numpy: 2.2.6
aiohttp: 3.12.14
fastapi: 0.116.1
hf_transfer: 0.1.9
huggingface_hub: 0.34.1
interegular: 0.3.3
modelscope: 1.28.1
orjson: 3.11.1
outlines: 0.1.11
packaging: 25.0
psutil: 7.0.0
pydantic: 2.11.7
python-multipart: 0.0.20
pyzmq: 27.0.0
uvicorn: 0.35.0
uvloop: 0.21.0
vllm: Module Not Found
xgrammar: 0.1.21
openai: Module Not Found
tiktoken: Module Not Found
anthropic: Module Not Found
litellm: Module Not Found
decord: Module Not Found
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 0-55,112-167 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 0-55,112-167 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 0-55,112-167 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 0-55,112-167 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 56-111,168-223 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 56-111,168-223 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 56-111,168-223 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X 56-111,168-223 1 N/A

Legend:

X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLinks

Hypervisor vendor: KVM
ulimit soft: 1048576

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions