[Bug]: Build vllm on Apple silicon: libc++abi error

[iervn6341-ovo]

Your current environment

The output of python collect_env.py

==============================
        System Info
==============================
OS                           : macOS 15.6.1 (arm64)
GCC version                  : Could not collect
Clang version                : 21.1.5
CMake version                : version 4.1.2
Libc version                 : N/A

==============================
       PyTorch Info
==============================
PyTorch version              : 2.8.0
Is debug build               : False
CUDA used to build PyTorch   : None
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.10.19 (main, Oct  9 2025, 15:25:03) [Clang 17.0.0 (clang-1700.0.13.3)] (64-bit runtime)
Python platform              : macOS-15.6.1-arm64-arm-64bit

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : False
CUDA runtime version         : No CUDA
CUDA_MODULE_LOADING set to   : N/A
GPU models and configuration : No CUDA
Nvidia driver version        : No CUDA
cuDNN version                : No CUDA
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
Apple M4 Pro

==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] pyzmq==27.1.0
[pip3] torch==2.8.0
[pip3] torchaudio==2.8.0
[pip3] torchvision==0.23.0
[pip3] transformers==4.57.1
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.11.1rc6
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     Environment Variables
==============================
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1

🐛 Describe the bug

After followed the vllm build instruction on official page, and successfully built the dependency.

And tried to run gemma3-4b model with vllm-cli (easy to setup vllm) on apple silicon.

then the terminal show below error:

Is there anyone facing the issue like me?

---

Full crash log

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.