[Bug] Cannot release memory

[yaoliliu]

Checklist

• 1. I have searched related issues but cannot get the expected help.
• 2. The bug has not been fixed in the latest version.
• 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

Describe the bug

model_id = "internlm/internlm3-8b-instruct-smoothquant-fp8"
pipe = lmdeploy.pipeline(model_id)
response = pipe("Please tell me five scenic spots in Shanghai")
del pipe

no memory was releasd:

|===========================================================================|
|                  PyTorch CUDA memory summary, device ID 0                 |
|---------------------------------------------------------------------------|
|            CUDA OOMs: 0            |        cudaMalloc retries: 0         |
|===========================================================================|
|        Metric         | Cur Usage  | Peak Usage | Tot Alloc  | Tot Freed  |
|---------------------------------------------------------------------------|
| Allocated memory      |  11986 MiB |  12247 MiB |  15882 MiB |   3895 MiB |
|---------------------------------------------------------------------------|
| Active memory         |  11986 MiB |  12247 MiB |  15882 MiB |   3895 MiB |
|---------------------------------------------------------------------------|
| Requested memory      |  11985 MiB |  12245 MiB |  15847 MiB |   3861 MiB |
|---------------------------------------------------------------------------|
| GPU reserved memory   |  12006 MiB |  12496 MiB |  12500 MiB | 505856 KiB |
|---------------------------------------------------------------------------|
| Non-releasable memory |  17413 KiB | 262326 KiB |  12157 MiB |  12140 MiB |
|---------------------------------------------------------------------------|
| Allocations           |     496    |     554    |   12214    |   11718    |
|---------------------------------------------------------------------------|
| Active allocs         |     496    |     554    |   12214    |   11718    |
|---------------------------------------------------------------------------|
| GPU reserved segments |     204    |     205    |     207    |       3    |
|---------------------------------------------------------------------------|
| Non-releasable allocs |      11    |      15    |    6675    |    6664    |
|---------------------------------------------------------------------------|
| Oversize allocations  |       0    |       0    |       0    |       0    |
|---------------------------------------------------------------------------|
| Oversize GPU segments |       0    |       0    |       0    |       0    |
|===========================================================================|

transformers version: 4.47.1 (I know lmdeploy require 4.46 and below, but this specific 'internlm/internlm3-8b-instruct-smoothquant-fp8' asks me to have at least 4.47.1 or it won't work)

Reproduction

model_id = "internlm/internlm3-8b-instruct-smoothquant-fp8"
pipe = lmdeploy.pipeline(model_id)
response = pipe("Please tell me five scenic spots in Shanghai")
del pipe
print(torch.cuda.memory_summary(device=torch.cuda.current_device(), abbreviated=True))

Environment

sys.platform: linux
Python: 3.12.0 | packaged by conda-forge | (main, Oct  3 2023, 08:43:22) [GCC 12.3.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3: NVIDIA GeForce RTX 4090
CUDA_HOME: /media/shared_space/liuyl/conda-forge/envs/flux
NVCC: Cuda compilation tools, release 12.4, V12.4.99
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.5.1+cu124
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 12.4
  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
  - CuDNN 90.1
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.4, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.5.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, 

TorchVision: 0.20.1+cu124
LMDeploy: 0.7.0+e896539
transformers: 4.47.1
gradio: Not Found
fastapi: 0.115.6
pydantic: 2.10.4
triton: 3.1.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NODE    SYS     SYS     0-35,72-107     0               N/A
GPU1    NODE     X      SYS     SYS     0-35,72-107     0               N/A
GPU2    SYS     SYS      X      NODE    36-71,108-143   1               N/A
GPU3    SYS     SYS     NODE     X      36-71,108-143   1               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

Error traceback