vllm: [Bug]: memory leak
Your current environment
The output of `python collect_env.py`
Collecting environment information...
PyTorch version: 2.4.0
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.26.4
Libc version: glibc-2.35
Python version: 3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-3.10.0-1160.71.1.el7.x86_64-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 GeForce RTX 3090
GPU 1: NVIDIA GeForce RTX 3090
Nvidia driver version: 535.129.03
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: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: GenuineIntel
BIOS Vendor ID: Red Hat
Model name: Intel(R) Xeon(R) Gold 6140M CPU @ 2.30GHz
BIOS Model name: RHEL 7.6.0 PC (i440FX + PIIX, 1996)
CPU family: 6
Model: 85
Thread(s) per core: 1
Core(s) per socket: 4
Socket(s): 4
Stepping: 4
BogoMIPS: 4599.99
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology eagerfpu pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 arat umip pku ospke md_clear spec_ctrl intel_stibp arch_capabilities
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 512 KiB (16 instances)
L1i cache: 512 KiB (16 instances)
L2 cache: 64 MiB (16 instances)
L3 cache: 64 MiB (4 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT disabled
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; Load fences, usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; IBRS (kernel), IBPB
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT Host state unknown
Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] nvidia-ml-py==12.560.30
[pip3] onnxruntime==1.16.3
[pip3] optree==0.12.1
[pip3] pyzmq==26.2.0
[pip3] sentence-transformers==3.0.1
[pip3] torch==2.4.0
[pip3] torchaudio==2.4.0
[pip3] torchelastic==0.2.2
[pip3] torchvision==0.19.0
[pip3] transformers==4.44.2
[pip3] transformers-stream-generator==0.0.4
[pip3] triton==3.0.0
[conda] blas 1.0 mkl
[conda] cuda-cudart 12.1.105 0 nvidia
[conda] cuda-cupti 12.1.105 0 nvidia
[conda] cuda-libraries 12.1.0 0 nvidia
[conda] cuda-nvrtc 12.1.105 0 nvidia
[conda] cuda-nvtx 12.1.105 0 nvidia
[conda] cuda-opencl 12.5.39 0 nvidia
[conda] cuda-runtime 12.1.0 0 nvidia
[conda] cuda-version 12.5 3 nvidia
[conda] ffmpeg 4.3 hf484d3e_0 pytorch
[conda] libcublas 12.1.0.26 0 nvidia
[conda] libcufft 11.0.2.4 0 nvidia
[conda] libcufile 1.10.1.7 0 nvidia
[conda] libcurand 10.3.6.82 0 nvidia
[conda] libcusolver 11.4.4.55 0 nvidia
[conda] libcusparse 12.0.2.55 0 nvidia
[conda] libjpeg-turbo 2.0.0 h9bf148f_0 pytorch
[conda] libnpp 12.0.2.50 0 nvidia
[conda] libnvjitlink 12.1.105 0 nvidia
[conda] libnvjpeg 12.1.1.14 0 nvidia
[conda] mkl 2023.1.0 h213fc3f_46344
[conda] mkl-service 2.4.0 py311h5eee18b_1
[conda] mkl_fft 1.3.8 py311h5eee18b_0
[conda] mkl_random 1.2.4 py311hdb19cb5_0
[conda] numpy 1.26.4 py311h08b1b3b_0
[conda] numpy-base 1.26.4 py311hf175353_0
[conda] nvidia-ml-py 12.560.30 pypi_0 pypi
[conda] optree 0.12.1 pypi_0 pypi
[conda] pytorch 2.4.0 py3.11_cuda12.1_cudnn9.1.0_0 pytorch
[conda] pytorch-cuda 12.1 ha16c6d3_5 pytorch
[conda] pytorch-mutex 1.0 cuda pytorch
[conda] pyzmq 26.2.0 pypi_0 pypi
[conda] sentence-transformers 3.0.1 pypi_0 pypi
[conda] torchaudio 2.4.0 py311_cu121 pytorch
[conda] torchelastic 0.2.2 pypi_0 pypi
[conda] torchtriton 3.0.0 py311 pytorch
[conda] torchvision 0.19.0 py311_cu121 pytorch
[conda] transformers 4.44.2 pypi_0 pypi
[conda] transformers-stream-generator 0.0.4 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.1.post2@9ba0817ff1eb514f51cc6de9cb8e16c98d6ee44f
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
GPU0 GPU1 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PHB 0-15 0 N/A
GPU1 PHB X 0-15 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
Model Input Dumps
No response
š Describe the bug
vllm serve /hestia/model/Qwen2.5-14B-Instruct-AWQ --max-model-len 16384 --quantization awq --port 8001 --swap-space 0 --served-model-name qwen --enable-auto-tool-choice --tool-call-parser hermes --num-gpu-blocks-override 1024
Before submitting a new issueā¦
- 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: open
- Created 2 years ago
- Comments: 15
Hi, is there any update on this? I encountered the same issue with the GPTQ model. After setting the utilization to 0.95 on a 40G GPU and running a few datasets, I experienced an out-of-memory error.
I tried triggering GC periodically through a plugin, but this didnāt solve the problem. I also observed this issue on version 0.6.0, but when I rolled back to 0.5.5, the problem disappeared. The same model ran for 6 hours on version 0.5.0, and with the same request volume, the memory peak never exceeded 4.5GB. So, the issue seems to have been introduced in version 0.6.0.