[Usage]: RuntimeError: Failed to infer device type (Intel Iris Xe Graphics)

[Noekar]

Your current environment

Collecting environment information...
WARNING 09-26 20:43:46 _custom_ops.py:18] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")
INFO 09-26 20:43:46 importing.py:10] Triton not installed; certain GPU-related functions will not be available.
C:\Users\sasha\vllm\vllm\vllm\connections.py:8: RuntimeWarning: Failed to read commit hash:
No module named 'vllm.commit_id'
  from vllm.version import __version__ as VLLM_VERSION
PyTorch version: 2.4.0+cpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 10 Enterprise
GCC version: Could not collect
Clang version: Could not collect
CMake version: Could not collect
Libc version: N/A

Python version: 3.10.14 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:44:50) [MSC v.1916 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.19045-SP0
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:
Architecture=9
CurrentClockSpeed=1800
DeviceID=CPU0
Family=198
L2CacheSize=4096
L2CacheSpeed=
Manufacturer=GenuineIntel
MaxClockSpeed=1800
Name=12th Gen Intel(R) Core(TM) i7-1265U
ProcessorType=3
Revision=

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-ml-py==12.560.30
[pip3] pyzmq==26.2.0
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.2
[conda] mkl                       2021.4.0                 pypi_0    pypi
[conda] numpy                     1.26.4                   pypi_0    pypi
[conda] nvidia-ml-py              12.560.30                pypi_0    pypi
[conda] pyzmq                     26.2.0                   pypi_0    pypi
[conda] torch                     2.4.0                    pypi_0    pypi
[conda] torchvision               0.19.0                   pypi_0    pypi
[conda] transformers              4.44.2                   pypi_0    pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.1.post2@COMMIT_HASH_PLACEHOLDER
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

My GPU : Intel(R) Iris(R) Xe Graphics / 15.8GB of shared memory

How would you like to use vllm

I want to run inference of a "mistralai/Pixtral-12B-2409" as shown here. Here below the code :

from vllm import LLM
from vllm.sampling_params import SamplingParams

model_name = "mistralai/Pixtral-12B-2409"

sampling_params = SamplingParams(max_tokens=8192)

llm = LLM(model=model_name, tokenizer_mode="mistral")

prompt = "Describe this image in one sentence."
image_url = "https://picsum.photos/id/237/200/300"

messages = [
    {
        "role": "user",
        "content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": image_url}}]
    },
]

outputs = vllm_model.model.chat(messages, sampling_params=sampling_params)

print(outputs[0].outputs[0].text)

This is what i got :

>>> llm = LLM(model=model_name, tokenizer_mode="mistral")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "C:\Users\sasha\vllm\vllm\vllm\entrypoints\llm.py", line 179, in __init__
    self.llm_engine = LLMEngine.from_engine_args(
  File "C:\Users\sasha\vllm\vllm\vllm\engine\llm_engine.py", line 552, in from_engine_args
    engine_config = engine_args.create_engine_config()
  File "C:\Users\sasha\vllm\vllm\vllm\engine\arg_utils.py", line 860, in create_engine_config
    device_config = DeviceConfig(device=self.device)
  File "C:\Users\sasha\vllm\vllm\vllm\config.py", line 1054, in __init__
    raise RuntimeError("Failed to infer device type")
RuntimeError: Failed to infer device type

Thanks,

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.

[mgoin]

I don't believe we support Intel(R) Iris(R) Xe Graphics with any backend, possibly OpenVINO? By default vLLM is built for NVIDIA GPUs

[sshlyapn]

Hi, @Noekar, you can try to use OpenVINO backend, it supports Intel(R) Iris(R) Xe Graphics as well: #8192

[smitedd]

A computer restart is needed after vllm installation in most cases. Otherwise the "Failed to infer device type" might display.

[pepijndevos]

I'm also facing the same issue trying to use the XPU target for Intel Arc A770:

$ python collect_env.py
WARNING 11-21 22:57:20 _custom_ops.py:20] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C'")
Collecting environment information...
PyTorch version: 2.6.0a0+gitae7f809
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Arch Linux (x86_64)
GCC version: (GCC) 14.2.1 20240910
Clang version: 18.1.8
CMake version: version 3.31.0
Libc version: glibc-2.40

Python version: 3.12.7 (main, Oct  1 2024, 11:15:50) [GCC 14.2.1 20240910] (64-bit runtime)
Python platform: Linux-6.11.9-arch1-1-x86_64-with-glibc2.40
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:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        48 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               32
On-line CPU(s) list:                  0-31
Vendor ID:                            AuthenticAMD
Model name:                           AMD Ryzen 9 7950X 16-Core Processor
CPU family:                           25
Model:                                97
Thread(s) per core:                   2
Core(s) per socket:                   16
Socket(s):                            1
Stepping:                             2
Frequency boost:                      enabled
CPU(s) scaling MHz:                   41%
CPU max MHz:                          4501,0000
CPU min MHz:                          400,0000
BogoMIPS:                             9003,92
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d amd_lbr_pmc_freeze
Virtualization:                       AMD-V
L1d cache:                            512 KiB (16 instances)
L1i cache:                            512 KiB (16 instances)
L2 cache:                             16 MiB (16 instances)
L3 cache:                             64 MiB (2 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-31
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:   Vulnerable: Safe RET, no microcode
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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] pyzmq==26.2.0
[pip3] torch==2.6.0a0+gitae7f809
[pip3] transformers==4.46.3
[pip3] triton==3.2.0+git3dd760bc
[conda] No relevant packages
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.5.dev4+g1d65ec7e.d20241121
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

VLLM_TARGET_DEVICE=xpu
LD_LIBRARY_PATH=/home/pepijn/code/llm/vllm/env/lib/python3.12/site-packages/cv2/../../lib64:/opt/intel/oneapi/tcm/1.2/lib:/opt/intel/oneapi/umf/0.9/lib:/opt/intel/oneapi/tbb/2022.0/env/../lib/intel64/gcc4.8:/opt/intel/oneapi/pti/0.10/lib:/opt/intel/oneapi/mpi/2021.14/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/2021.14/lib:/opt/intel/oneapi/mkl/2025.0/lib:/opt/intel/oneapi/ippcp/2025.0/lib/:/opt/intel/oneapi/ipp/2022.0/lib:/opt/intel/oneapi/dnnl/2025.0/lib:/opt/intel/oneapi/debugger/2025.0/opt/debugger/lib:/opt/intel/oneapi/dal/2025.0/lib:/opt/intel/oneapi/compiler/2025.0/opt/oclfpga/host/linux64/lib:/opt/intel/oneapi/compiler/2025.0/opt/compiler/lib:/opt/intel/oneapi/compiler/2025.0/lib:/opt/intel/oneapi/ccl/2021.14/lib/

[pepijndevos]

I tried OpenVINO but the instructions don't seem to build Intel GPU support, so even in Docker I get all sorts of errors.

[zejun-chen]

If using CPU, you can specify the device when creating LLM handler.
llm = LLM(model=model_dir, device='cpu')

[ilya-lavrenov]

I tried OpenVINO but the instructions don't seem to build Intel GPU support, so even in Docker I get all sorts of errors.

Hi @pepijndevos ,
Could you please provide errors? Build instruction assumes a build with OpenVINO support, while pip's openvino package has support for both CPU and GPU, so both devices should be available with a single build step.

[pepijndevos]

I believe the problem may have been with the version of userland intel drivers. I can run openvino on GPU now.

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!

[github-actions]

This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!