Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.3 LTS (aarch64)
GCC version                  : (Ubuntu 12.4.0-2ubuntu1~24.04.1) 12.4.0
Clang version                : 18.1.3 (1ubuntu1)
CMake version                : version 4.3.2
Libc version                 : glibc-2.39

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cpu
Is debug build               : False
CUDA used to build PyTorch   : None
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.13 (main, May 10 2026, 19:27:23) [Clang 22.1.3 ] (64-bit runtime)
Python platform              : Linux-6.17.0-1013-aws-aarch64-with-glibc2.39

==============================
       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
==============================
Architecture:                            aarch64
CPU op-mode(s):                    64-bit
Byte Order:                              Little Endian
CPU(s):                                    96
On-line CPU(s) list:                0-95
Vendor ID:                               ARM
Model name:                           Neoverse-V2
Model:                                     1
Thread(s) per core:                1
Core(s) per socket:                96
Socket(s):                               1
Stepping:                                r0p1
BogoMIPS:                             2000.00
Flags:                                     fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               6 MiB (96 instances)
L1i cache:                               6 MiB (96 instances)
L2 cache:                                192 MiB (96 instances)
L3 cache:                                36 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-95
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                Not affected
Vulnerability Indirect target selection: 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 Old microcode:             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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.3.5
[pip3] pyzmq==27.1.0
[pip3] torch==2.11.0+cpu
[pip3] torchaudio==2.11.0+cpu
[pip3] torchvision==0.26.0+cpu
[pip3] transformers==5.8.1
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.21.1rc1.dev70+g47829b115.d20260521 (git sha: 47829b115, date: 20260521)
vLLM-Omni Version            : N/A (vllm_omni not installed)
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
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_gausah01

---

AssertionError: MoEActivation.GELU_TANH is not supported.

---

VLLM_TARGET_DEVICE=cpu \
vllm bench throughput \
  --model google/gemma-4-26B-A4B-it \
  --dataset-name sonnet \
  --dataset-path vllm_source/benchmarks/sonnet.txt \
  --num-prompts 1 \
  --max-model-len 2048 \
  --override-generation-config '{"temperature": "0.0", "top_p": "1.0"}'

---

vLLM CPU engine should initialize and run the benchmark for google/gemma-4-26B-A4B-it.

---

Engine initialization fails because GELU_TANH is not supported in the CPU fused MoE activation mapping.

---

torch._dynamo.exc.Unsupported: Observed exception

Developer debug context:
raised exception AssertionError([ConstantVariable(str: 'MoEActivation.GELU_TANH is not supported.')])

from user code:
  File ".../vllm/model_executor/models/gemma4.py", line 1330, in forward
    hidden_states, residual = layer(

  File ".../vllm/model_executor/models/gemma4.py", line 732, in forward
    hidden_states_2 = self.moe(hidden_states_2, router_logits)

  File ".../vllm/model_executor/models/gemma4.py", line 365, in forward
    return self.experts(x, router_logits)

  File ".../vllm/model_executor/layers/fused_moe/layer.py", line 1311, in forward
    return self.runner.forward(

  File ".../vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py", line 354, in apply_monolithic
    return self.cpu_fused_moe(

  File ".../vllm/model_executor/layers/fused_moe/cpu_fused_moe.py", line 261, in __call__
    assert activation in _CPU_MOE_ACT_FN, f"{activation} is not supported."

---

vllm/model_executor/layers/fused_moe/activation.py

---

vllm/model_executor/layers/fused_moe/cpu_fused_moe.py

---

_CPU_MOE_ACT_FN = {
    MoEActivation.SILU: ...,
    MoEActivation.SWIGLUOAI: ...,
    MoEActivation.GELU: _gelu_and_mul,
}