[Bug]: `RuntimeError: Failed to infer device type` with v0.7.2 #12847

imangohari1 · 2025-02-06T19:19:08Z

Your current environment

The output of `python collect_env.py`

INFO 02-06 18:50:45 __init__.py:194] No platform detected, vLLM is running on UnspecifiedPlatform
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.1 LTS (x86_64)
GCC version: (Ubuntu 13.2.0-23ubuntu4) 13.2.0
Clang version: Could not collect
CMake version: version 3.31.1
Libc version: glibc-2.39

Python version: 3.12.3 (main, Nov  6 2024, 18:32:19) [GCC 13.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-52-generic-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A100 80GB PCIe
Nvidia driver version: 565.57.01
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.6.0
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):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
BIOS Vendor ID:                       Intel(R) Corporation
Model name:                           Intel(R) Xeon(R) Platinum 8480+
BIOS Model name:                      Intel(R) Xeon(R) Platinum 8480+  CPU @ 2.0GHz
BIOS CPU family:                      179
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             6
CPU(s) scaling MHz:                   25%
CPU max MHz:                          3800.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4000.00
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 rep_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 avx512_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:                            5.3 MiB (112 instances)
L1i cache:                            3.5 MiB (112 instances)
L2 cache:                             224 MiB (112 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-55,112-167
NUMA node1 CPU(s):                    56-111,168-223
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] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[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-cudnn-frontend==1.8.0
[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-dali-cuda120==1.44.0
[pip3] nvidia-ml-py==12.570.86
[pip3] nvidia-modelopt==0.21.0
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvimgcodec-cu12==0.3.0.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] nvidia-pyindex==1.0.9
[pip3] onnx==1.17.0
[pip3] optree==0.13.1
[pip3] pynvml==11.4.1
[pip3] pytorch-triton==3.0.0+72734f086
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torch_tensorrt==2.6.0a0
[pip3] torchaudio==2.5.1
[pip3] torchprofile==0.0.4
[pip3] torchvision==0.20.1
[pip3] transformers==4.48.2
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.7.3.dev10+g467a96a5
vLLM Build Flags:
CUDA Archs: 7.0 7.5 8.0 8.6 9.0+PTX; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      0-55,112-167    0               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=all
CUBLAS_VERSION=12.6.4.1
NVIDIA_REQUIRE_CUDA=cuda>=9.0
CUDA_CACHE_DISABLE=1
TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.6 9.0+PTX
NCCL_VERSION=2.23.4
NVIDIA_DRIVER_CAPABILITIES=compute,utility,video
NVIDIA_PRODUCT_NAME=PyTorch
CUDA_VERSION=12.6.3.004
PYTORCH_VERSION=2.6.0a0+df5bbc0
PYTORCH_BUILD_NUMBER=0
CUDNN_FRONTEND_VERSION=1.8.0
CUDNN_VERSION=9.6.0.74
PYTORCH_HOME=/opt/pytorch/pytorch
LD_LIBRARY_PATH=/usr/local/lib/python3.12/dist-packages/torch/lib:/usr/local/lib/python3.12/dist-packages/torch_tensorrt/lib:/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
NVIDIA_BUILD_ID=126674149
CUDA_DRIVER_VERSION=560.35.05
PYTORCH_BUILD_VERSION=2.6.0a0+df5bbc0
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
CUDA_MODULE_LOADING=LAZY
NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=
NVIDIA_PYTORCH_VERSION=24.12
TORCH_ALLOW_TF32_CUBLAS_OVERRIDE=1
NCCL_CUMEM_ENABLE=0
TORCHINDUCTOR_COMPILE_THREADS=1

🐛 Describe the bug

Using the main branch on commit 467a96a5415dc896170cecc0bb83d9c49c2f3c5e, we are facing RuntimeError: Failed to infer device type. The details of the env/test is given below.

Note

This issue does NOT happen using 0.7.1 release. On the same machine, same container, changing the installation to pip install vllm (or pip install https://github.com/vllm-project/vllm/releases/download/v0.7.1/vllm-0.7.1-cp38-abi3-manylinux1_x86_64.whl) works fine.

Container/Setup

Container: nvcr.io/nvidia/pytorch:24.12-py3
Setup:

git clone https://github.com/vllm-project/vllm.git
cd vllm
VLLM_USE_PRECOMPILED=1 pip install --editable .

Test

python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 8000 --model meta-llama/Llama-3.2-3B-Instruct --seed 42 -tp 1 --use-v2-block-manager --max_model_len 2048

INFO 02-06 19:18:33 __init__.py:194] No platform detected, vLLM is running on UnspecifiedPlatform
INFO 02-06 19:18:34 api_server.py:840] vLLM API server version 0.7.3.dev10+g467a96a5
INFO 02-06 19:18:34 api_server.py:841] args: Namespace(host='0.0.0.0', port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, enable_reasoning=False, reasoning_parser=None, tool_call_parser=None, tool_parser_plugin='', model='meta-llama/Llama-3.2-3B-Instruct', task='auto', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=2048, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=42, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=None, qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', generation_config=None, override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False)
INFO 02-06 19:18:34 api_server.py:206] Started engine process with PID 879
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/tmp/vllm/vllm/entrypoints/openai/api_server.py", line 911, in <module>
    uvloop.run(run_server(args))
  File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 194, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/usr/local/lib/python3.12/dist-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/tmp/vllm/vllm/entrypoints/openai/api_server.py", line 875, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/vllm/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/vllm/vllm/entrypoints/openai/api_server.py", line 217, in build_async_engine_client_from_engine_args
    engine_config = engine_args.create_engine_config()
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/vllm/vllm/engine/arg_utils.py", line 1074, in create_engine_config
    device_config = DeviceConfig(device=self.device)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/vllm/vllm/config.py", line 1626, in __init__
    raise RuntimeError("Failed to infer device type")

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.

The text was updated successfully, but these errors were encountered:

youkaichao · 2025-02-07T01:30:19Z

looks strange. I think #12809 should solve it. the actual error should raise earlier.

youkaichao · 2025-02-07T01:32:58Z

INFO 02-06 18:50:45 init.py:194] No platform detected, vLLM is running on UnspecifiedPlatform

this is the problem.

can you try to follow

vllm/vllm/utils.py

Line 2223 in b260782

def import_pynvml():

to see why it happens?

[pip3] nvidia-ml-py==12.570.86
[pip3] pynvml==11.4.1

since you have both pynvml and nvidia-ml-py, I think the code above should work. Not sure why it does not work for your case.

lizongyao123 · 2025-02-07T01:50:54Z

升级pynvml到12.0.0即可。

pip install -U pynvml

youkaichao · 2025-02-07T02:09:35Z

@lizongyao123 @imangohari1 can you install the latest release (0.7.2 has been released) and see if it happens again? I think the latest release should work even if you have pynvml < 12

ghosthamlet · 2025-02-07T02:14:58Z

@lizongyao123 @imangohari1 can you install the latest release (0.7.2 has been released) and see if it happens again? I think the latest release should work even if you have pynvml < 12

I have same problem: No platform detected, vLLM is running on UnspecifiedPlatform
vllm 0.7.2
Run import_pynvml()
RuntimeError: You are using a deprecated pynvmlpackage. Please uninstallpynvml or upgrade to at least version 12.0. See https://pypi.org/project/pynvml for more information.

After ungrade pynvml to 12.0.0
Fix it.

zimoqingfeng · 2025-02-07T02:15:41Z

@lizongyao123 @imangohari1 can you install the latest release (0.7.2 has been released) and see if it happens again? I think the latest release should work even if you have pynvml < 12

It may not work when I use vllm=0.7.2 & pynvml==11.5.3

2catycm · 2025-02-07T02:33:21Z

I encountered similar problem

2catycm · 2025-02-07T02:36:10Z

Very good issue，I also succeeded to fix this by uv pip install pynvml==12.0.0

youkaichao · 2025-02-07T03:08:15Z

@ghosthamlet are you using vllm serve , or use vllm as a library inside a python file?

youkaichao · 2025-02-07T03:11:51Z

If anyone can give me a reproducible example, that would be great. In addition, feel free to join https://slack.vllm.ai for quick communication.

imangohari1 · 2025-02-07T16:28:39Z

@youkaichao

If anyone can give me a reproducible example, that would be great. In addition, feel free to join https://slack.vllm.ai for quick communication.

I have included a reproducer in the #12847 (comment).
Have you tried this?
~~I am gonna try to join the slack channel.~~ I can't join the slack channel due to internal policy restrictions :/

imangohari1 · 2025-02-07T16:54:06Z

@lizongyao123 @imangohari1 can you install the latest release (0.7.2 has been released) and see if it happens again? I think the latest release should work even if you have pynvml < 12

@youkaichao I redid the test with 0.7.2 release with pynvml 11.4.1, and still fails.

Note

The only workaround right now is to update pynvml to 12.0.0 with pip install -U pynvml

youkaichao · 2025-02-07T17:09:47Z

@imangohari1 thanks! I find the root cause, the docker image nvcr.io/nvidia/pytorch:24.12-py3 includes pynvml==11.4.1

imangohari1 · 2025-02-07T18:27:32Z

@imangohari1 thanks! I find the root cause, the docker image nvcr.io/nvidia/pytorch:24.12-py3 includes pynvml==11.4.1

Thanks, Two points here:

I checked with nvcr.io/nvidia/pytorch:25.01-py3, which is the latest pt container from NGC, and still has the same pynvml version.

NOTE: CUDA Forward Compatibility mode ENABLED.
  Using CUDA 12.8 driver version 570.86.10 with kernel driver version 565.57.01.
  See https://docs.nvidia.com/deploy/cuda-compatibility/ for details.

root@8a2c3a5bdaba:# pip list| grep pyvnml
pynvml                     11.4.1

why the v0.7.1 works fine with the pyvnml==11.4.1 version and only >v0.7.2 having issue?

qmzznbxhl · 2025-02-08T02:01:11Z

升级pynvml到12.0.0即可。

pip install -U pynvml

same error，really work by update “pip install pynvml==12.0.0”

MangoFF · 2025-02-08T03:00:06Z

It works for me, “pip install pynvml==12.0.0”

Stonesjtu · 2025-02-08T08:11:37Z

@youkaichao should we pin the pynvml version in requirements.txt for next bugfix release?
The same error occurs for the newest pypi 0.7.2 version

youkaichao · 2025-02-08T17:04:07Z

I found the culprint:

when pynvml < 12 and nvidia-ml-py are both installed, although vllm handles it well, pytorch will use a simple import pynvml which will import the wrong version (the first one, unofficial one).

To avoid the issue completely, I opened #12963 .

youkaichao · 2025-02-09T06:58:33Z

@Stonesjtu we cannot pin pynvml==12.0 since that will make vllm conflict with other libraries. please check #12977

imangohari1 · 2025-02-10T16:35:20Z

@youkaichao
Thanks for the update.
I can see that the issue of undefied platform is resolved but now I am getting another issue:

ERROR 02-10 16:02:30 registry.py:307] /usr/local/lib/python3.12/dist-packages/flash_attn_2_cuda.cpython-312-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE

Should I open a separate ticket for this?

imangohari1 · 2025-02-10T17:17:30Z

@youkaichao Thanks for the update. I can see that the issue of undefied platform is resolved but now I am getting another issue:
ERROR 02-10 16:02:30 registry.py:307] /usr/local/lib/python3.12/dist-packages/flash_attn_2_cuda.cpython-312-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE
Should I open a separate ticket for this?

I opened a new issue for this. #13047

josephzucc · 2025-02-11T10:32:55Z

Hi, i just download vllm on a ubuntu linux 11feb 11:32 spanish hour, and it just happen the same error.

dcrockwell · 2025-02-12T13:56:08Z

Exact same issue with 0.7.3.dev94+g985b4a2b.d20250212.neuron216 compiled from source for neuron on an inferentia instance.

$ vllm serve meta-llama/Llama-3.1-8B-Instruct --served-model-name ceto --max-model-len 2048  --tensor-parallel-size 12 --gpu-memory-utilization=0.9
INFO 02-12 14:03:53 __init__.py:194] No platform detected, vLLM is running on UnspecifiedPlatform
INFO 02-12 14:03:53 api_server.py:840] vLLM API server version 0.7.3.dev94+g985b4a2b.d20250212
INFO 02-12 14:03:53 api_server.py:841] args: Namespace(subparser='serve', model_tag='meta-llama/Llama-3.1-8B-Instruct', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key=None, lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, enable_reasoning=False, reasoning_parser=None, tool_call_parser=None, tool_parser_plugin='', model='meta-llama/Llama-3.1-8B-Instruct', task='auto', tokenizer=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=False, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=2048, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=12, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=0, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.9, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['ceto'], qlora_adapter_name_or_path=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', generation_config=None, override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, additional_config=None, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, dispatch_function=<function serve at 0x7f1128dc77f0>)
INFO 02-12 14:03:53 api_server.py:206] Started engine process with PID 11349
Traceback (most recent call last):
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/bin/vllm", line 8, in <module>
    sys.exit(main())
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/scripts.py", line 204, in main
    args.dispatch_function(args)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/scripts.py", line 44, in serve
    uvloop.run(run_server(args))
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/uvloop/__init__.py", line 82, in run
    return loop.run_until_complete(wrapper())
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 875, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/usr/lib/python3.10/contextlib.py", line 199, in __aenter__
    return await anext(self.gen)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 136, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/usr/lib/python3.10/contextlib.py", line 199, in __aenter__
    return await anext(self.gen)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 217, in build_async_engine_client_from_engine_args
    engine_config = engine_args.create_engine_config()
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 1090, in create_engine_config
    device_config = DeviceConfig(device=self.device)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/config.py", line 1630, in __init__
    raise RuntimeError("Failed to infer device type")
RuntimeError: Failed to infer device type
INFO 02-12 14:03:57 __init__.py:194] No platform detected, vLLM is running on UnspecifiedPlatform
ERROR 02-12 14:03:57 engine.py:389] Failed to infer device type
ERROR 02-12 14:03:57 engine.py:389] Traceback (most recent call last):
ERROR 02-12 14:03:57 engine.py:389]   File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
ERROR 02-12 14:03:57 engine.py:389]     engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
ERROR 02-12 14:03:57 engine.py:389]   File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
ERROR 02-12 14:03:57 engine.py:389]     engine_config = engine_args.create_engine_config(usage_context)
ERROR 02-12 14:03:57 engine.py:389]   File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 1090, in create_engine_config
ERROR 02-12 14:03:57 engine.py:389]     device_config = DeviceConfig(device=self.device)
ERROR 02-12 14:03:57 engine.py:389]   File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/config.py", line 1630, in __init__
ERROR 02-12 14:03:57 engine.py:389]     raise RuntimeError("Failed to infer device type")
ERROR 02-12 14:03:57 engine.py:389] RuntimeError: Failed to infer device type
Process SpawnProcess-1:
Traceback (most recent call last):
  File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine
    raise e
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 380, in run_mp_engine
    engine = MQLLMEngine.from_engine_args(engine_args=engine_args,
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/multiprocessing/engine.py", line 118, in from_engine_args
    engine_config = engine_args.create_engine_config(usage_context)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 1090, in create_engine_config
    device_config = DeviceConfig(device=self.device)
  File "/opt/aws_neuronx_venv_pytorch_2_5_nxd_inference/lib/python3.10/site-packages/vllm/config.py", line 1630, in __init__
    raise RuntimeError("Failed to infer device type")
RuntimeError: Failed to infer device type

vkudryk · 2025-02-16T02:54:43Z

Getting the same error trying to run on Gaudi HPU.

xiayouran · 2025-02-18T05:13:01Z

the same error on V100.

…0785) Two dependencies we are resolving that requires to pin `xgrammar` and `pynvml` to specific versions. Related vllm PR/ issues - vllm-project/vllm#13338 - vllm-project/vllm#12847 --------- Signed-off-by: Gene Su <[email protected]>

…y-project#50785) Two dependencies we are resolving that requires to pin `xgrammar` and `pynvml` to specific versions. Related vllm PR/ issues - vllm-project/vllm#13338 - vllm-project/vllm#12847 --------- Signed-off-by: Gene Su <[email protected]> Signed-off-by: kaihsun <[email protected]>

rlrs · 2025-03-02T10:42:24Z

I'm seeing the same thing on ROCm after building from source. Will try an earlier version.

Update: amdsmi must be installed, but isn't mentioned in the installation instructions. Ensure that the version matches your ROCm version.

…y-project#50785) Two dependencies we are resolving that requires to pin `xgrammar` and `pynvml` to specific versions. Related vllm PR/ issues - vllm-project/vllm#13338 - vllm-project/vllm#12847 --------- Signed-off-by: Gene Su <[email protected]>

youkaichao · 2025-03-04T10:40:43Z

for people who met this issue, I added lots of debug logging in #14195 . please set VLLM_LOGGING_LEVEL=DEBUG and check why a specific platform is not recognized.

…y-project#50785) Two dependencies we are resolving that requires to pin `xgrammar` and `pynvml` to specific versions. Related vllm PR/ issues - vllm-project/vllm#13338 - vllm-project/vllm#12847 --------- Signed-off-by: Gene Su <[email protected]>

…y-project#50785) Two dependencies we are resolving that requires to pin `xgrammar` and `pynvml` to specific versions. Related vllm PR/ issues - vllm-project/vllm#13338 - vllm-project/vllm#12847 --------- Signed-off-by: Gene Su <[email protected]> Signed-off-by: Jay Chia <[email protected]>

geraldstanje · 2025-03-20T22:52:53Z

@youkaichao i see the following in the debug log for vllm/vllm-openai:v0.8.1 image.
can i run vllm/vllm-openai:v0.8.1 with cpu only? how to set the device to cpu?

DEBUG 03-20 22:46:23 [__init__.py:28] No plugins for group vllm.platform_plugins found.
DEBUG 03-20 22:46:23 [__init__.py:35] Checking if TPU platform is available.
DEBUG 03-20 22:46:23 [__init__.py:45] TPU platform is not available because: No module named 'libtpu'
DEBUG 03-20 22:46:23 [__init__.py:53] Checking if CUDA platform is available.
DEBUG 03-20 22:46:23 [__init__.py:77] Exception happens when checking CUDA platform: NVML Shared Library Not Found
DEBUG 03-20 22:46:23 [__init__.py:94] CUDA platform is not available because: NVML Shared Library Not Found
DEBUG 03-20 22:46:23 [__init__.py:101] Checking if ROCm platform is available.
DEBUG 03-20 22:46:23 [__init__.py:115] ROCm platform is not available because: No module named 'amdsmi'
DEBUG 03-20 22:46:23 [__init__.py:123] Checking if HPU platform is available.
DEBUG 03-20 22:46:23 [__init__.py:130] HPU platform is not available because habana_frameworks is not found.
DEBUG 03-20 22:46:23 [__init__.py:141] Checking if XPU platform is available.
DEBUG 03-20 22:46:23 [__init__.py:151] XPU platform is not available because: No module named 'intel_extension_for_pytorch'
DEBUG 03-20 22:46:23 [__init__.py:159] Checking if CPU platform is available.
DEBUG 03-20 22:46:23 [__init__.py:181] Checking if Neuron platform is available.
DEBUG 03-20 22:46:23 [__init__.py:188] Neuron platform is not available because: No module named 'transformers_neuronx'
DEBUG 03-20 22:46:23 [__init__.py:196] Checking if OpenVINO platform is available.
DEBUG 03-20 22:46:23 [__init__.py:203] OpenVINO platform is not available because vLLM is not built with OpenVINO.
INFO 03-20 22:46:23 [__init__.py:260] No platform detected, vLLM is running on UnspecifiedPlatform

it looks like i need to build cpu image for vllm/vllm-openai:v0.8.1 myself - is there some doc to build the image?

youkaichao · 2025-03-22T06:13:01Z

can i run vllm/vllm-openai:v0.8.1 with cpu only?

no.

XYZliang · 2025-03-25T19:39:54Z

same in h200 with BAAI/bge-m3, but works fine with llms like QwQ:
docker-compose:

version: '3.9'

services:
  vllm-server:
    image: vllm/vllm-openai:latest
    container_name: vllm-emb
    runtime: nvidia
    environment:
      # - CUDA_VISIBLE_DEVICES=6,7
      # - VLLM_USE_V1=1
      - VLLM_LOGGING_LEVEL=DEBUG
    volumes:
      - /data/sdv1/model:/model
      - ~/.cache/huggingface:/root/.cache/huggingface
    ports:
      - "8003:8000"
    ipc: host
    entrypoint: /bin/sh
    command: 
      - -c
      - |
        pip install -U pynvml && \
        vllm serve /model/BAAI/bge-m3 \
          --port 8000 \
          --api-key ***@123 \
          --trust-remote-code \
          --seed 2024 \
          --gpu-memory-utilization 0.95 \
          --served-model-name BAAI/bge-m3
      # "--tensor-parallel-size", "2",
      # "--dtype", "bfloat16"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]

docker logs:

Collecting pynvml
  Downloading pynvml-12.0.0-py3-none-any.whl.metadata (5.4 kB)
Collecting nvidia-ml-py<13.0.0a0,>=12.0.0 (from pynvml)
  Downloading nvidia_ml_py-12.570.86-py3-none-any.whl.metadata (8.7 kB)
Downloading pynvml-12.0.0-py3-none-any.whl (26 kB)
Downloading nvidia_ml_py-12.570.86-py3-none-any.whl (44 kB)
Installing collected packages: nvidia-ml-py, pynvml
Successfully installed nvidia-ml-py-12.570.86 pynvml-12.0.0
DEBUG 03-25 19:38:26 [__init__.py:28] No plugins for group vllm.platform_plugins found.
DEBUG 03-25 19:38:26 [__init__.py:35] Checking if TPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:45] TPU platform is not available because: No module named 'libtpu'
DEBUG 03-25 19:38:26 [__init__.py:53] Checking if CUDA platform is available.
DEBUG 03-25 19:38:26 [__init__.py:77] Exception happens when checking CUDA platform: NVML Shared Library Not Found
DEBUG 03-25 19:38:26 [__init__.py:94] CUDA platform is not available because: NVML Shared Library Not Found
DEBUG 03-25 19:38:26 [__init__.py:101] Checking if ROCm platform is available.
DEBUG 03-25 19:38:26 [__init__.py:115] ROCm platform is not available because: No module named 'amdsmi'
DEBUG 03-25 19:38:26 [__init__.py:123] Checking if HPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:130] HPU platform is not available because habana_frameworks is not found.
DEBUG 03-25 19:38:26 [__init__.py:141] Checking if XPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:151] XPU platform is not available because: No module named 'intel_extension_for_pytorch'
DEBUG 03-25 19:38:26 [__init__.py:159] Checking if CPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:181] Checking if Neuron platform is available.
DEBUG 03-25 19:38:26 [__init__.py:188] Neuron platform is not available because: No module named 'transformers_neuronx'
DEBUG 03-25 19:38:26 [__init__.py:196] Checking if OpenVINO platform is available.
DEBUG 03-25 19:38:26 [__init__.py:203] OpenVINO platform is not available because vLLM is not built with OpenVINO.
INFO 03-25 19:38:26 [__init__.py:260] No platform detected, vLLM is running on UnspecifiedPlatform
DEBUG 03-25 19:38:28 [main.py:50] Setting VLLM_WORKER_MULTIPROC_METHOD to 'spawn'
DEBUG 03-25 19:38:28 [__init__.py:28] No plugins for group vllm.general_plugins found.
INFO 03-25 19:38:28 [api_server.py:977] vLLM API server version 0.8.1
INFO 03-25 19:38:28 [api_server.py:978] args: Namespace(subparser='serve', model_tag='/model/BAAI/bge-m3', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key='***@123', lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='/model/BAAI/bge-m3', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=True, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=2024, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.95, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, use_tqdm_on_load=True, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['BAAI/bge-m3'], qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, additional_config=None, enable_reasoning=False, reasoning_parser=None, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False, dispatch_function=<function ServeSubcommand.cmd at 0x7f3977f9ae80>)
Traceback (most recent call last):
  File "/opt/venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main
    args.dispatch_function(args)
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 33, in cmd
    uvloop.run(run_server(args))
  File "/opt/venv/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/asyncio/runners.py", line 195, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/opt/venv/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1012, in run_server
    async with build_async_engine_client(args) as engine_client:
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 141, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 161, in build_async_engine_client_from_engine_args
    vllm_config = engine_args.create_engine_config(usage_context=usage_context)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1205, in create_engine_config
    device_config = DeviceConfig(device=self.device)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/config.py", line 1798, in __init__
    raise RuntimeError("Failed to infer device type")
RuntimeError: Failed to infer device type

docker images from docker pull vllm/vllm-openai:v0.8.1

XYZliang · 2025-03-26T08:45:01Z

same in h200 with BAAI/bge-m3, but works fine with llms like QwQ: docker-compose:

version: '3.9'

services:
  vllm-server:
    image: vllm/vllm-openai:latest
    container_name: vllm-emb
    runtime: nvidia
    environment:
      # - CUDA_VISIBLE_DEVICES=6,7
      # - VLLM_USE_V1=1
      - VLLM_LOGGING_LEVEL=DEBUG
    volumes:
      - /data/sdv1/model:/model
      - ~/.cache/huggingface:/root/.cache/huggingface
    ports:
      - "8003:8000"
    ipc: host
    entrypoint: /bin/sh
    command: 
      - -c
      - |
        pip install -U pynvml && \
        vllm serve /model/BAAI/bge-m3 \
          --port 8000 \
          --api-key ***@123 \
          --trust-remote-code \
          --seed 2024 \
          --gpu-memory-utilization 0.95 \
          --served-model-name BAAI/bge-m3
      # "--tensor-parallel-size", "2",
      # "--dtype", "bfloat16"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]

docker logs:

Collecting pynvml
  Downloading pynvml-12.0.0-py3-none-any.whl.metadata (5.4 kB)
Collecting nvidia-ml-py<13.0.0a0,>=12.0.0 (from pynvml)
  Downloading nvidia_ml_py-12.570.86-py3-none-any.whl.metadata (8.7 kB)
Downloading pynvml-12.0.0-py3-none-any.whl (26 kB)
Downloading nvidia_ml_py-12.570.86-py3-none-any.whl (44 kB)
Installing collected packages: nvidia-ml-py, pynvml
Successfully installed nvidia-ml-py-12.570.86 pynvml-12.0.0
DEBUG 03-25 19:38:26 [__init__.py:28] No plugins for group vllm.platform_plugins found.
DEBUG 03-25 19:38:26 [__init__.py:35] Checking if TPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:45] TPU platform is not available because: No module named 'libtpu'
DEBUG 03-25 19:38:26 [__init__.py:53] Checking if CUDA platform is available.
DEBUG 03-25 19:38:26 [__init__.py:77] Exception happens when checking CUDA platform: NVML Shared Library Not Found
DEBUG 03-25 19:38:26 [__init__.py:94] CUDA platform is not available because: NVML Shared Library Not Found
DEBUG 03-25 19:38:26 [__init__.py:101] Checking if ROCm platform is available.
DEBUG 03-25 19:38:26 [__init__.py:115] ROCm platform is not available because: No module named 'amdsmi'
DEBUG 03-25 19:38:26 [__init__.py:123] Checking if HPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:130] HPU platform is not available because habana_frameworks is not found.
DEBUG 03-25 19:38:26 [__init__.py:141] Checking if XPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:151] XPU platform is not available because: No module named 'intel_extension_for_pytorch'
DEBUG 03-25 19:38:26 [__init__.py:159] Checking if CPU platform is available.
DEBUG 03-25 19:38:26 [__init__.py:181] Checking if Neuron platform is available.
DEBUG 03-25 19:38:26 [__init__.py:188] Neuron platform is not available because: No module named 'transformers_neuronx'
DEBUG 03-25 19:38:26 [__init__.py:196] Checking if OpenVINO platform is available.
DEBUG 03-25 19:38:26 [__init__.py:203] OpenVINO platform is not available because vLLM is not built with OpenVINO.
INFO 03-25 19:38:26 [__init__.py:260] No platform detected, vLLM is running on UnspecifiedPlatform
DEBUG 03-25 19:38:28 [main.py:50] Setting VLLM_WORKER_MULTIPROC_METHOD to 'spawn'
DEBUG 03-25 19:38:28 [__init__.py:28] No plugins for group vllm.general_plugins found.
INFO 03-25 19:38:28 [api_server.py:977] vLLM API server version 0.8.1
INFO 03-25 19:38:28 [api_server.py:978] args: Namespace(subparser='serve', model_tag='/model/BAAI/bge-m3', config='', host=None, port=8000, uvicorn_log_level='info', allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key='***@123', lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='/model/BAAI/bge-m3', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=True, allowed_local_media_path=None, download_dir=None, load_format='auto', config_format=<ConfigFormat.AUTO: 'auto'>, dtype='auto', kv_cache_dtype='auto', max_model_len=None, guided_decoding_backend='xgrammar', logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, block_size=None, enable_prefix_caching=None, disable_sliding_window=False, use_v2_block_manager=True, num_lookahead_slots=0, seed=2024, swap_space=4, cpu_offload_gb=0, gpu_memory_utilization=0.95, num_gpu_blocks_override=None, max_num_batched_tokens=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, max_num_seqs=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, disable_custom_all_reduce=False, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config=None, limit_mm_per_prompt=None, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=False, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=False, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', num_scheduler_steps=1, use_tqdm_on_load=True, multi_step_stream_outputs=True, scheduler_delay_factor=0.0, enable_chunked_prefill=None, speculative_model=None, speculative_model_quantization=None, num_speculative_tokens=None, speculative_disable_mqa_scorer=False, speculative_draft_tensor_parallel_size=None, speculative_max_model_len=None, speculative_disable_by_batch_size=None, ngram_prompt_lookup_max=None, ngram_prompt_lookup_min=None, spec_decoding_acceptance_method='rejection_sampler', typical_acceptance_sampler_posterior_threshold=None, typical_acceptance_sampler_posterior_alpha=None, disable_logprobs_during_spec_decoding=None, model_loader_extra_config=None, ignore_patterns=[], preemption_mode=None, served_model_name=['BAAI/bge-m3'], qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, scheduling_policy='fcfs', scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config=None, enable_sleep_mode=False, calculate_kv_scales=False, additional_config=None, enable_reasoning=False, reasoning_parser=None, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False, dispatch_function=<function ServeSubcommand.cmd at 0x7f3977f9ae80>)
Traceback (most recent call last):
  File "/opt/venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main
    args.dispatch_function(args)
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 33, in cmd
    uvloop.run(run_server(args))
  File "/opt/venv/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run
    return __asyncio.run(
           ^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/asyncio/runners.py", line 195, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/opt/venv/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1012, in run_server
    async with build_async_engine_client(args) as engine_client:
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 141, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/uv/python/cpython-3.12.9-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 161, in build_async_engine_client_from_engine_args
    vllm_config = engine_args.create_engine_config(usage_context=usage_context)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1205, in create_engine_config
    device_config = DeviceConfig(device=self.device)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/venv/lib/python3.12/site-packages/vllm/config.py", line 1798, in __init__
    raise RuntimeError("Failed to infer device type")
RuntimeError: Failed to infer device type

docker images from docker pull vllm/vllm-openai:v0.8.1

I think I have found the problem, I have upgraded my docker, and now I need to remove the colon in docker-compose.

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]

Everything is normal now.

Clement25 · 2025-04-03T16:16:40Z

I solved by manually designating the device type in initialization

llm = LLM('model_name', device=cuda)

imangohari1 added the bug Something isn't working label Feb 6, 2025

DarkLight1337 mentioned this issue Feb 7, 2025

[Usage]: #12861

Closed

1 task

youkaichao mentioned this issue Feb 8, 2025

[core] port pynvml into vllm codebase #12963

Merged

youkaichao mentioned this issue Feb 9, 2025

[RFC]: copy pynvml code into vllm codebase #12977

Closed

1 task

youkaichao closed this as completed in #12963 Feb 9, 2025

imangohari1 mentioned this issue Feb 10, 2025

[Bug]: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE when running 0.7.3.dev57+g2ae88905.precompiled on A100 #13047

Open

1 task

GeneDer mentioned this issue Feb 21, 2025

[llm.serving] Address dependencies related issues for llm serving ray-project/ray#50785

Merged

8 tasks

kaiserdan mentioned this issue Mar 26, 2025

Multi-node Ray LUMI - Did not find socket name .. in the list of object store socket names. CSCfi/ai-inference-examples#1

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Bug]: `RuntimeError: Failed to infer device type` with v0.7.2 #12847

[Bug]: `RuntimeError: Failed to infer device type` with v0.7.2 #12847

imangohari1 commented Feb 6, 2025

Before submitting a new issue...

youkaichao commented Feb 7, 2025

youkaichao commented Feb 7, 2025

lizongyao123 commented Feb 7, 2025

youkaichao commented Feb 7, 2025

ghosthamlet commented Feb 7, 2025

zimoqingfeng commented Feb 7, 2025

2catycm commented Feb 7, 2025

2catycm commented Feb 7, 2025

youkaichao commented Feb 7, 2025

youkaichao commented Feb 7, 2025

imangohari1 commented Feb 7, 2025 •

edited

Loading

imangohari1 commented Feb 7, 2025

youkaichao commented Feb 7, 2025

imangohari1 commented Feb 7, 2025

qmzznbxhl commented Feb 8, 2025

MangoFF commented Feb 8, 2025

Stonesjtu commented Feb 8, 2025

youkaichao commented Feb 8, 2025

youkaichao commented Feb 9, 2025

imangohari1 commented Feb 10, 2025

imangohari1 commented Feb 10, 2025

josephzucc commented Feb 11, 2025

dcrockwell commented Feb 12, 2025 •

edited

Loading

vkudryk commented Feb 16, 2025

xiayouran commented Feb 18, 2025

rlrs commented Mar 2, 2025 •

edited

Loading

youkaichao commented Mar 4, 2025

geraldstanje commented Mar 20, 2025 •

edited

Loading

youkaichao commented Mar 22, 2025

XYZliang commented Mar 25, 2025 •

edited

Loading

XYZliang commented Mar 26, 2025

Clement25 commented Apr 3, 2025

[Bug]: RuntimeError: Failed to infer device type with v0.7.2 #12847

[Bug]: RuntimeError: Failed to infer device type with v0.7.2 #12847

Comments

imangohari1 commented Feb 6, 2025

Your current environment

🐛 Describe the bug

Before submitting a new issue...

youkaichao commented Feb 7, 2025

youkaichao commented Feb 7, 2025

lizongyao123 commented Feb 7, 2025

youkaichao commented Feb 7, 2025

ghosthamlet commented Feb 7, 2025

zimoqingfeng commented Feb 7, 2025

2catycm commented Feb 7, 2025

2catycm commented Feb 7, 2025

youkaichao commented Feb 7, 2025

youkaichao commented Feb 7, 2025

imangohari1 commented Feb 7, 2025 • edited Loading

imangohari1 commented Feb 7, 2025

youkaichao commented Feb 7, 2025

imangohari1 commented Feb 7, 2025

qmzznbxhl commented Feb 8, 2025

MangoFF commented Feb 8, 2025

Stonesjtu commented Feb 8, 2025

youkaichao commented Feb 8, 2025

youkaichao commented Feb 9, 2025

imangohari1 commented Feb 10, 2025

imangohari1 commented Feb 10, 2025

josephzucc commented Feb 11, 2025

dcrockwell commented Feb 12, 2025 • edited Loading

vkudryk commented Feb 16, 2025

xiayouran commented Feb 18, 2025

rlrs commented Mar 2, 2025 • edited Loading

youkaichao commented Mar 4, 2025

geraldstanje commented Mar 20, 2025 • edited Loading

youkaichao commented Mar 22, 2025

XYZliang commented Mar 25, 2025 • edited Loading

XYZliang commented Mar 26, 2025

Clement25 commented Apr 3, 2025

[Bug]: `RuntimeError: Failed to infer device type` with v0.7.2 #12847

[Bug]: `RuntimeError: Failed to infer device type` with v0.7.2 #12847

imangohari1 commented Feb 7, 2025 •

edited

Loading

dcrockwell commented Feb 12, 2025 •

edited

Loading

rlrs commented Mar 2, 2025 •

edited

Loading

geraldstanje commented Mar 20, 2025 •

edited

Loading

XYZliang commented Mar 25, 2025 •

edited

Loading