vllm: Tool calls not triggered properly with vLLM 0.8.5 and Qwen2.5-Coder-32B-Instruct-GPTQ-Int4

Your current environment

The output of python collect_env.py
INFO 05-07 17:26:12 [__init__.py:239] Automatically detected platform cuda.
Collecting environment information...
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 4.0.0
Libc version: glibc-2.35

Python version: 3.12.10 (main, Apr  9 2025, 08:55:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.8.0-35-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3

Nvidia driver version: 550.54.15
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               192
On-line CPU(s) list:                  0-191
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8468
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   48
Socket(s):                            2
Stepping:                             8
CPU max MHz:                          3800.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4200.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts re
p_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
 rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt
_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx
512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect
cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            4.5 MiB (96 instances)
L1i cache:                            3 MiB (96 instances)
L2 cache:                             192 MiB (96 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-47,96-143
NUMA node1 CPU(s):                    48-95,144-191
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] flashinfer-python==0.2.1.post2+cu124torch2.6
[pip3] numpy==2.2.5
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.4.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.6.0
[pip3] torchvision==0.21.0
[pip3] transformers==4.51.3
[pip3] triton==3.2.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.8.5
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV18    NV18    NV18    0-47,96-143     0               N/A
GPU1    NV18     X      NV18    NV18    0-47,96-143     0               N/A
GPU2    NV18    NV18     X      NV18    48-95,144-191   1               N/A
GPU3    NV18    NV18    NV18     X      48-95,144-191   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

NVIDIA_VISIBLE_DEVICES=GPU-6a4a45dc-ecb9-6afd-7352-32af35190639,GPU-61cd127b-e2e7-08f6-2a43-7f247e84d08b,GPU-5459e040-6673-7776-06b4-456c2b7a9dcd,GPU-72602610-166f-a3c2-1bd5-ecd36e81bddd
NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforce
rtx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driv
er>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,drive
r>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,d
river<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driv
er<536
NCCL_VERSION=2.20.5-1
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_PRODUCT_NAME=CUDA
VLLM_USAGE_SOURCE=production-docker-image
CUDA_VERSION=12.4.0
NVIDIA_DISABLE_REQUIRE=true
LD_LIBRARY_PATH=/usr/lib/nvidia:/usr/lib/x86_64-linux-gnu
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY

šŸ› Describe the bug

Hi team,

I am running vllm version 0.8.5 with the following launch command:

vllm serve Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4 \
  --quantization gptq \
  --download-dir /models \
  --tensor-parallel-size 4 \
  --enable-auto-tool-choice \
  --tool-call-parser hermes

I am trying to test function calling (tool calling) with the model (Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4), sending the following request body (for example, via Postman):

{
    "model": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4",
    "messages": [
        {
            "role": "system",
            "content": "you are helpful ai"
        },
        {
            "role": "user",
            "content": "what is the weather in seoul?"
        }
    ],
    "stream": false,
    "tool_choice": "auto",
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather in a given location",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "location": {
                            "type": "string",
                            "description": "City and state, e.g., 'San Francisco, CA'"
                        },
                        "unit": {
                            "type": "string",
                            "enum": [
                                "celsius",
                                "fahrenheit"
                            ]
                        }
                    },
                    "required": [
                        "location",
                        "unit"
                    ]
                }
            }
        }
    ]
}

However, I’m seeing the following issue:
Instead of getting an actual tool_call in the response, this is what I get:

"choices": [
    {
        "index": 0,
        "message": {
            "role": "assistant",
            "reasoning_content": null,
            "content": "{\"name\": \"get_weather\", \"arguments\": {\"location\": \"Seoul, South Korea\", \"unit\": \"celsius\"}}",
            "tool_calls": []
        },
        "logprobs": null,
        "finish_reason": "stop",
        "stop_reason": null
    }
],

So, the function is being output as a string in the assistant’s message content, and the tool_calls field is empty. It seems that the tool calling logic is not being triggered as expected, even though I’m sending tool_choice: "auto" and passed --enable-auto-tool-choice to vllm serve.

Before submitting a new issue…

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

About this issue

  • Original URL
  • State: open
  • Created 2 years ago
  • Comments: 23 (13 by maintainers)

Most upvoted comments

@codeMonkey-shin By default, vLLM uses the v1 engine for inference. You need to set the environment variable VLLM_USE_V1=0 to switch vLLM’s engine to v0, please refer to this: https://docs.vllm.ai/en/v0.8.1/getting_started/v1_user_guide.html.

Later, I will try to fix the bug with function call parsing in the v1 engine, if it’s only a v1 engine bug.