Qwen3-30B-A3B tool-call-parser

[miniboxhaha]

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

which tool-call-parser should use for Qwen3-30B-A3B?
qwen25 seems not work as expect.
vllm use hermes works fine.

Reproduction

python3 -m sglang.launch_server --model-path /home/ubuntu/huggingface/hub/models--Qwen--Qwen3-30B-A3B/snapshots/ae659febe817e4b3ebd7355f47792725801204c9 --base-gpu-id 7 --host 0.0.0.0 --port 18000 --api-key qweasdzxc --tool-call-parser qwen25

Environment

Python: 3.11.3 (main, Apr 19 2023, 23:54:32) [GCC 11.2.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA A800 80GB PCIe
GPU 0,1,2,3,4,5,6,7 Compute Capability: 8.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.4, V12.4.99
CUDA Driver Version: 550.90.07
PyTorch: 2.7.1+cu126
sglang: 0.4.8.post1
sgl_kernel: 0.1.9
flashinfer_python: 0.2.6.post1
triton: 3.3.1
transformers: 4.52.3
torchao: 0.9.0
numpy: 1.24.3
aiohttp: 3.12.13
fastapi: 0.115.14
hf_transfer: 0.1.9
huggingface_hub: 0.33.2
interegular: 0.3.3
modelscope: 1.27.1
orjson: 3.10.7
outlines: 0.1.11
packaging: 23.0
psutil: 5.9.0
pydantic: 2.8.2
python-multipart: 0.0.9
pyzmq: 27.0.0
uvicorn: 0.30.6
uvloop: 0.21.0
vllm: Module Not Found
xgrammar: 0.1.19
openai: 1.93.0
tiktoken: 0.7.0
anthropic: 0.57.1
litellm: 1.73.6.post1
decord: 0.6.0
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PIX PIX PIX SYS SYS SYS SYS 0-35,72-107 0 N/A
GPU1 PIX X PIX PIX SYS SYS SYS SYS 0-35,72-107 0 N/A
GPU2 PIX PIX X PIX SYS SYS SYS SYS 0-35,72-107 0 N/A
GPU3 PIX PIX PIX X SYS SYS SYS SYS 0-35,72-107 0 N/A
GPU4 SYS SYS SYS SYS X PIX PIX PIX 36-71,108-143 1 N/A
GPU5 SYS SYS SYS SYS PIX X PIX PIX 36-71,108-143 1 N/A
GPU6 SYS SYS SYS SYS PIX PIX X PIX 36-71,108-143 1 N/A
GPU7 SYS SYS SYS SYS PIX PIX PIX X 36-71,108-143 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

ulimit soft: 1024

[AndrewChen9527]

I’m running into the same issue: the tool_call tags occasionally show up in “content”. but they’re rarely parsed into the tool_calls field.

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen it if needed.

[Violettttee]

@AndrewChen9527 Hi，have you solved this problems? I also found the same situation.

[Pablonara]

Also running into this issue, curious if anyone has found a solution?