vllm
vllm copied to clipboard
Published
20 hours ago •
vllm-project
vllm-project
[Bug]: vllm/vllm/_C.cpython-310-x86_64-linux-gnu.so: undefined symbol error
Your current environment
The output of `python collect_env.py`
Collecting environment information...
PyTorch version: 2.1.2+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.27.6
Libc version: glibc-2.35
Python version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-73-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.2.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090
Nvidia driver version: 535.104.05
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.5
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.5
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: 46 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 64
On-line CPU(s) list: 0-63
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
CPU family: 6
Model: 106
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 2
Stepping: 6
CPU max MHz: 3500.0000
CPU min MHz: 800.0000
BogoMIPS: 5800.00
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 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 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 1.5 MiB (32 instances)
L1i cache: 1 MiB (32 instances)
L2 cache: 40 MiB (32 instances)
L3 cache: 48 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-15,32-47
NUMA node1 CPU(s): 16-31,48-63
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed: Not affected
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; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.22.2
[pip3] onnx==1.14.0
[pip3] pytorch-quantization==2.1.2
[pip3] torch==2.1.2
[pip3] torch-tensorrt==0.0.0
[pip3] torchdata==0.7.0a0
[pip3] torchtext==0.16.0a0
[pip3] torchvision==0.16.0a0
[pip3] triton==2.1.0+e621604
[conda] Could not collectROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: N/A
vLLM Build Flags:
CUDA Archs: 5.2 6.0 6.1 7.0 7.2 7.5 8.0 8.6 8.7 9.0+PTX; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 NIC0 NIC1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NODE NODE 0-15,32-47 0 N/A
NIC0 NODE X PIX
NIC1 NODE PIX 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
How you are installing vllm
pip install -i http://ftp.daumkakao.com/pypi/simple --trusted-host ftp.daumkakao.com -e .
I tried to import vllm,but it failed.
python
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import vllm
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/sjlim/workspace/vllm/vllm/__init__.py", line 3, in <module>
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs,
File "/home/sjlim/workspace/vllm/vllm/engine/arg_utils.py", line 6, in <module>
from vllm.config import (CacheConfig, ModelConfig, ParallelConfig,
File "/home/sjlim/workspace/vllm/vllm/config.py", line 9, in <module>
from vllm.utils import get_cpu_memory
File "/home/sjlim/workspace/vllm/vllm/utils.py", line 8, in <module>
from vllm._C import cuda_utils
ImportError: /home/sjlim/workspace/vllm/vllm/_C.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops19empty_memory_format4callEN3c108ArrayRefINS2_6SymIntEEESt8optionalINS2_10ScalarTypeEES6_INS2_6LayoutEES6_INS2_6DeviceEES6_IbES6_INS2_12MemoryFormatEE
It would be better if you can give a full installation log via pip install -i http://ftp.daumkakao.com/pypi/simple --trusted-host ftp.daumkakao.com -v -e .
i.e. adding -v flag .
Thanks for letting me know. But the problem now is that the pip install ends successfully, but when I import, I get the same problem as above. I will fix the tag as bug.
If your import fails, it is also in installation problem. We cannot help further without more details :(
When you install vllm using pip, you might frequently run into errors related to 'undefined symbol', often because of conflicting versions with pytorch or something.
It's safer to build vllm from the source. https://github.com/vllm-project/vllm/issues/129#issuecomment-1805088950
I built it from the source. still i get the undefined symbol error (recent HEAD commit of main branch)
root@b0da1a1ca0fd:~# python3
Python 3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 16:04:32) [GCC 12.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import triton
>>> import vllm
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/root/vllm/vllm/__init__.py", line 4, in <module>
from vllm.engine.async_llm_engine import AsyncLLMEngine
File "/root/vllm/vllm/engine/async_llm_engine.py", line 12, in <module>
from vllm.engine.llm_engine import LLMEngine
File "/root/vllm/vllm/engine/llm_engine.py", line 16, in <module>
from vllm.model_executor.model_loader import get_architecture_class_name
File "/root/vllm/vllm/model_executor/model_loader.py", line 10, in <module>
from vllm.model_executor.models.llava import LlavaForConditionalGeneration
File "/root/vllm/vllm/model_executor/models/llava.py", line 11, in <module>
from vllm.model_executor.layers.activation import get_act_fn
File "/root/vllm/vllm/model_executor/layers/activation.py", line 9, in <module>
from vllm._C import ops
ImportError: /root/vllm/vllm/_C.cpython-310-powerpc64le-linux-gnu.so: undefined symbol: cuPointerGetAttribute
Let me know if any information is needed or if creating a new issue seems to be good
build the container with DOCKER_BUILDKIT=0, the probelm will be solved. (building needs gpu)