vllm: [Usage]: zmq.error.ZMQError: Operation not supported

Your current environment

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

Python version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-130-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA A100-SXM4-40GB
GPU 1: NVIDIA A100-SXM4-40GB
GPU 2: NVIDIA A100-SXM4-40GB
GPU 3: NVIDIA A100-SXM4-40GB
GPU 4: NVIDIA A100-SXM4-40GB
GPU 5: NVIDIA A100-SXM4-40GB
GPU 6: NVIDIA A100-SXM4-40GB
GPU 7: NVIDIA A100-SXM4-40GB

Nvidia driver version: 550.127.08
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:                        45 bits physical, 48 bits virtual
Byte Order:                           Little Endian
CPU(s):                               8
On-line CPU(s) list:                  0-7
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 7742 64-Core Processor
CPU family:                           23
Model:                                49
Thread(s) per core:                   1
Core(s) per socket:                   1
Socket(s):                            8
Stepping:                             0
BogoMIPS:                             4491.56
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero wbnoinvd arat umip rdpid overflow_recov succor
Hypervisor vendor:                    VMware
Virtualization type:                  full
L1d cache:                            256 KiB (8 instances)
L1i cache:                            256 KiB (8 instances)
L2 cache:                             4 MiB (8 instances)
L3 cache:                             128 MiB (8 instances)
NUMA node(s):                         1
NUMA node0 CPU(s):                    0-7
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:               Mitigation; untrained return thunk; SMT disabled
Vulnerability Spec rstack overflow:   Mitigation; SMT disabled
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Retpolines; IBPB conditional; STIBP disabled; 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] 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-ml-py==12.560.30
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] transformers==4.47.1
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.6.post1
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV12    NV12    NV12    NV12    NV12    NV12    NV12    0-7     0               N/A
GPU1    NV12     X      NV12    NV12    NV12    NV12    NV12    NV12    0-7     0               N/A
GPU2    NV12    NV12     X      NV12    NV12    NV12    NV12    NV12    0-7     0               N/A
GPU3    NV12    NV12    NV12     X      NV12    NV12    NV12    NV12    0-7     0               N/A
GPU4    NV12    NV12    NV12    NV12     X      NV12    NV12    NV12    0-7     0               N/A
GPU5    NV12    NV12    NV12    NV12    NV12     X      NV12    NV12    0-7     0               N/A
GPU6    NV12    NV12    NV12    NV12    NV12    NV12     X      NV12    0-7     0               N/A
GPU7    NV12    NV12    NV12    NV12    NV12    NV12    NV12     X      0-7     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

NCCL_DEBUG=TRACE
CUDA_LAUNCH_BLOCKING=1
VLLM_TRACE_FUNCTION=1
VLLM_LOGGING_LEVEL=DEBUG
LD_LIBRARY_PATH=/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/cv2/../../lib64:
CUDA_MODULE_LOADING=LAZY

How would you like to use vllm

I want to run inference of a meta-llama/Llama-3.1-70B-Instruct. I don’t know how to integrate it with vllm.

When I try to launch the vLLM engine using the OpenAI-compatible API server, the server fails to start, and I see multiple ZMQError(“Operation not supported”) exceptions in the log. Eventually, the process exits with a RuntimeError: Engine process failed to start.

I attempted to run vLLM using the OpenAI-compatible API server with the following command:

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m vllm.entrypoints.openai.api_server \
--gpu-memory-utilization 0.95 \
--model=meta-llama/Llama-3.1-70B-Instruct \
--tensor-parallel-size 8 \
--max-model-len=8192 \
--max-num-seqs=8 \
--enforce_eager \
--host=0.0.0.0 --port=8000

However, the server fails to start and repeatedly logs ZMQError(“Operation not supported”) before exiting with:

Below are the full error logs

Task exception was never retrieved
future: <Task finished name='Task-2' coro=<MQLLMEngineClient.run_output_handler_loop() done, defined at /home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py:178> exception=ZMQError('Operation not supported')>
Traceback (most recent call last):
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py", line 184, in run_output_handler_loop
    while await self.output_socket.poll(timeout=VLLM_RPC_TIMEOUT
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/zmq/_future.py", line 400, in poll
    raise _zmq.ZMQError(_zmq.ENOTSUP)
zmq.error.ZMQError: Operation not supported
Task exception was never retrieved
future: <Task finished name='Task-3' coro=<MQLLMEngineClient.run_output_handler_loop() done, defined at /home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py:178> exception=ZMQError('Operation not supported')>
Traceback (most recent call last):
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py", line 184, in run_output_handler_loop
    while await self.output_socket.poll(timeout=VLLM_RPC_TIMEOUT
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/zmq/_future.py", line 400, in poll
    raise _zmq.ZMQError(_zmq.ENOTSUP)
zmq.error.ZMQError: Operation not supported
Task exception was never retrieved
future: <Task finished name='Task-4' coro=<MQLLMEngineClient.run_output_handler_loop() done, defined at /home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py:178> exception=ZMQError('Operation not supported')>
Traceback (most recent call last):
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py", line 184, in run_output_handler_loop
    while await self.output_socket.poll(timeout=VLLM_RPC_TIMEOUT
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/zmq/_future.py", line 400, in poll
    raise _zmq.ZMQError(_zmq.ENOTSUP)
zmq.error.ZMQError: Operation not supported
Task exception was never retrieved
future: <Task finished name='Task-5' coro=<MQLLMEngineClient.run_output_handler_loop() done, defined at /home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py:178> exception=ZMQError('Operation not supported')>
Traceback (most recent call last):
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py", line 184, in run_output_handler_loop
    while await self.output_socket.poll(timeout=VLLM_RPC_TIMEOUT
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/zmq/_future.py", line 400, in poll
    raise _zmq.ZMQError(_zmq.ENOTSUP)
zmq.error.ZMQError: Operation not supported
Task exception was never retrieved
future: <Task finished name='Task-6' coro=<MQLLMEngineClient.run_output_handler_loop() done, defined at /home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py:178> exception=ZMQError('Operation not supported')>
Traceback (most recent call last):
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/engine/multiprocessing/client.py", line 184, in run_output_handler_loop
    while await self.output_socket.poll(timeout=VLLM_RPC_TIMEOUT
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/zmq/_future.py", line 400, in poll
    raise _zmq.ZMQError(_zmq.ENOTSUP)
zmq.error.ZMQError: Operation not supported
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 774, in <module>
    uvloop.run(run_server(args))
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/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 "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
  File "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 740, 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 "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 118, 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 "/home/ubuntu/.cache/pypoetry/virtualenvs/ubuntu-zk_aSFMD-py3.10/lib/python3.10/site-packages/vllm/entrypoints/openai/api_server.py", line 223, in build_async_engine_client_from_engine_args
    raise RuntimeError(
RuntimeError: Engine process failed to start. See stack trace for the root cause.

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: closed
  • Created 2 years ago
  • Reactions: 1
  • Comments: 20 (6 by maintainers)

Most upvoted comments

Hi there, I met the same issue, this also happens when I switched to sglang. I noticed both of them, in my case, use nccl 2.21.5, and all of you are using nccl 2.21.5. So I updated my pip package nvidia-nccl-cu12 to a higher version. Then the problem is solved. Try it and see if it works.sion: 2.18.5-1-2

I didn’t find exactly the same solution, but something close. On my cloud provider, I tested two different OS images for LLaMA 3.1 70B-FP8 (same configuration GPU, CPU, RAM): • Ubuntu 22.04 (2023.12.04-0) / NCCL 2.21.5 → Doesn’t work • Ubuntu 24.04 (2024.11.28-0) / NCCL 2.21.5 → Works

The root cause of this issue is obviously a package version that may need to be updated, not just the vram capability.

Hi there, I met the same issue, this also happens when I switched to sglang. I noticed both of them, in my case, use nccl 2.21.5, and all of you are using nccl 2.21.5. So I updated my pip package nvidia-nccl-cu12 to a higher version. Then the problem is solved. Try it and see if it works.