[Bug]: pplx-kernels fails to load in vLLM container #30003
Description
Your current environment
The output of python collect_env.py
==============================
System Info
==============================
OS : Ubuntu 22.04.5 LTS (aarch64)
GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
Clang version : Could not collect
CMake version : Could not collect
Libc version : glibc-2.35
==============================
PyTorch Info
==============================
PyTorch version : 2.9.0+cu130
Is debug build : False
CUDA used to build PyTorch : 13.0
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.12 (main, Oct 10 2025, 08:52:57) [GCC 11.4.0] (64-bit runtime)
Python platform : Linux-6.8.0-1028-nvidia-64k-aarch64-with-glibc2.35
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 13.0.88
CUDA_MODULE_LOADING set to :
GPU models and configuration :
GPU 0: NVIDIA GB200
GPU 1: NVIDIA GB200
GPU 2: NVIDIA GB200
GPU 3: NVIDIA GB200
Nvidia driver version : 580.95.05
cuDNN version : Could not collect
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): 144
On-line CPU(s) list: 0-143
Vendor ID: ARM
Model name: Neoverse-V2
Model: 0
Thread(s) per core: 1
Core(s) per socket: 72
Socket(s): 2
Stepping: r0p0
Frequency boost: disabled
CPU max MHz: 3429.0000
CPU min MHz: 81.0000
BogoMIPS: 2000.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm ssbs sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh bti
L1d cache: 9 MiB (144 instances)
L1i cache: 9 MiB (144 instances)
L2 cache: 144 MiB (144 instances)
L3 cache: 228 MiB (2 instances)
NUMA node(s): 34
NUMA node0 CPU(s): 0-71
NUMA node1 CPU(s): 72-143
NUMA node2 CPU(s):
NUMA node3 CPU(s):
NUMA node4 CPU(s):
NUMA node5 CPU(s):
NUMA node6 CPU(s):
NUMA node7 CPU(s):
NUMA node8 CPU(s):
NUMA node9 CPU(s):
NUMA node10 CPU(s):
NUMA node11 CPU(s):
NUMA node12 CPU(s):
NUMA node13 CPU(s):
NUMA node14 CPU(s):
NUMA node15 CPU(s):
NUMA node16 CPU(s):
NUMA node17 CPU(s):
NUMA node18 CPU(s):
NUMA node19 CPU(s):
NUMA node20 CPU(s):
NUMA node21 CPU(s):
NUMA node22 CPU(s):
NUMA node23 CPU(s):
NUMA node24 CPU(s):
NUMA node25 CPU(s):
NUMA node26 CPU(s):
NUMA node27 CPU(s):
NUMA node28 CPU(s):
NUMA node29 CPU(s):
NUMA node30 CPU(s):
NUMA node31 CPU(s):
NUMA node32 CPU(s):
NUMA node33 CPU(s):
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; __user pointer sanitization
Vulnerability Spectre v2: Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.5.3
[pip3] numpy==2.2.6
[pip3] nvidia-cublas==13.0.0.19
[pip3] nvidia-cuda-cupti==13.0.48
[pip3] nvidia-cuda-nvrtc==13.0.48
[pip3] nvidia-cuda-runtime==13.0.48
[pip3] nvidia-cudnn-cu13==9.13.0.50
[pip3] nvidia-cudnn-frontend==1.16.0
[pip3] nvidia-cufft==12.0.0.15
[pip3] nvidia-cufile==1.15.0.42
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.3.29
[pip3] nvidia-cusparse==12.6.2.49
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-cutlass-dsl==4.3.1
[pip3] nvidia-ml-py==13.580.82
[pip3] nvidia-nccl-cu13==2.27.7
[pip3] nvidia-nvjitlink==13.0.39
[pip3] nvidia-nvshmem-cu13==3.3.24
[pip3] nvidia-nvtx==13.0.39
[pip3] pyzmq==27.1.0
[pip3] torch==2.9.0+cu130
[pip3] torchaudio==2.9.0
[pip3] torchvision==0.24.0
[pip3] transformers==4.57.3
[pip3] triton==3.5.0
[conda] Could not collect
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.1.dev11876+g506ed87e8 (git sha: 506ed87e8)
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 GPU1 GPU2 GPU3 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NODE NODE NODE SYS SYS SYS 0-71 0 N/A
GPU1 NV18 X NV18 NV18 NODE NODE NODE SYS SYS SYS 0-71 0 N/A
GPU2 NV18 NV18 X NV18 SYS SYS SYS NODE NODE NODE 72-143 1 N/A
GPU3 NV18 NV18 NV18 X SYS SYS SYS NODE NODE NODE 72-143 1 N/A
NIC0 NODE NODE SYS SYS X NODE NODE SYS SYS SYS
NIC1 NODE NODE SYS SYS NODE X NODE SYS SYS SYS
NIC2 NODE NODE SYS SYS NODE NODE X SYS SYS SYS
NIC3 SYS SYS NODE NODE SYS SYS SYS X NODE NODE
NIC4 SYS SYS NODE NODE SYS SYS SYS NODE X NODE
NIC5 SYS SYS NODE NODE SYS SYS SYS NODE NODE X
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
NIC Legend:
NIC0: mlx5_0
NIC1: mlx5_1
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
==============================
Environment Variables
==============================
CUDA_VERSION=13.0.1
CUDA_VISIBLE_DEVICES=0,1,2,3
CUDA_VISIBLE_DEVICES=0,1,2,3
LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NCCL_CUMEM_ENABLE=1
NCCL_DEBUG=WARN
NCCL_IB_DISABLE=0
NCCL_IB_HCA=mlx5_0,mlx5_1,mlx5_3,mlx5_4
NCCL_IB_SL=1
NCCL_IB_TIMEOUT=24
NCCL_MNNVL_ENABLE=1
NCCL_NET_GDR_C2C=1
NCCL_NET_PLUGIN=None
NCCL_NVLS_ENABLE=0
NCCL_SHM_DISABLE=0
NCCL_SOCKET_IFNAME=eth0
NVIDIA_DRIVER_CAPABILITIES=all
NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
NVIDIA_VISIBLE_DEVICES=all
VLLM_USAGE_SOURCE=production-docker-image
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
🐛 Describe the bug
Using the vLLM container on CUDA 13.0, built with:
DOCKER_BUILDKIT=1 docker build \
--build-arg max_jobs=24 \
--build-arg nvcc_threads=2 \
--build-arg RUN_WHEEL_CHECK=false \
--build-arg CUDA_VERSION=13.0.1 \
--build-arg BUILD_BASE_IMAGE=nvidia/cuda:13.0.1-devel-ubuntu22.04 \
--build-arg FLASHINFER_AOT_COMPILE=true \
--build-arg torch_cuda_arch_list='9.0 10.0+PTX' \
--build-arg INSTALL_KV_CONNECTORS=true \
--platform "linux/arm64" \
--target vllm-openai \
--progress plain \
-f docker/Dockerfile \
.
pplx-kernels fails to load when serving RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4:
vllm serve RedHatAI/Qwen3-VL-235B-A22B-Instruct-NVFP4 -dp 2 --mm-encoder-tp-mode data --async-scheduling --max-model-len 32768
The following error is thrown (after which the checkpoint continues to load):
(EngineCore_DP0 pid=3040376) [2025-12-03 14:55:53] ERROR ops.py:16: Error loading pplx-kernels
(EngineCore_DP0 pid=3040376) Traceback (most recent call last):
(EngineCore_DP0 pid=3040376) File "/usr/local/lib/python3.12/dist-packages/torch/_ops.py", line 1488, in load_library
(EngineCore_DP0 pid=3040376) ctypes.CDLL(path)
(EngineCore_DP0 pid=3040376) File "/usr/lib/python3.12/ctypes/__init__.py", line 379, in __init__
(EngineCore_DP0 pid=3040376) self._handle = _dlopen(self._name, mode)
(EngineCore_DP0 pid=3040376) ^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP0 pid=3040376) OSError: /usr/local/lib/python3.12/dist-packages/pplx_kernels/libpplx_kernels.so: undefined symbol: cudaGetDeviceProperties_v2
(EngineCore_DP0 pid=3040376)
(EngineCore_DP0 pid=3040376) The above exception was the direct cause of the following exception:
(EngineCore_DP0 pid=3040376)
(EngineCore_DP0 pid=3040376) Traceback (most recent call last):
(EngineCore_DP0 pid=3040376) File "/usr/local/lib/python3.12/dist-packages/pplx_kernels/ops.py", line 10, in <module>
(EngineCore_DP0 pid=3040376) torch.ops.load_library(_lib_path)
(EngineCore_DP0 pid=3040376) File "/usr/local/lib/python3.12/dist-packages/torch/_ops.py", line 1490, in load_library
(EngineCore_DP0 pid=3040376) raise OSError(f"Could not load this library: {path}") from e
(EngineCore_DP0 pid=3040376) OSError: Could not load this library: /usr/local/lib/python3.12/dist-packages/pplx_kernels/libpplx_kernels.so
This is due to libpplx_kernels.so contains the symbol cudaGetDeviceProperties_v2 which is deprecated in CUDA 13.0. This symbol would otherwise exist in prior versions of CUDA, such as 12.8.
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.