[Bug] 加载internvl2-26B遇到language_model.output.weight进度为92%但卡住的情况

Checklist

[X] 1. I have searched related issues but cannot get the expected help.
[X] 2. The bug has not been fixed in the latest version.
[X] 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

0%| | 0/12 [00:00<?, ?w/s] mlp1.0.bias: 0%| | 0/12 [00:00<?, ?w/s, dev=1] mlp1.0.weight: 8%|▊ | 1/12 [00:00<00:00, 1929.30w/s, dev=1] mlp1.1.bias: 17%|█▋ | 2/12 [00:00<00:00, 2973.63w/s, dev=1]
mlp1.1.weight: 25%|██▌ | 3/12 [00:00<00:00, 3777.52w/s, dev=1] mlp1.3.bias: 33%|███▎ | 4/12 [00:00<00:00, 152.38w/s, dev=1]
mlp1.3.weight: 42%|████▏ | 5/12 [00:00<00:00, 187.57w/s, dev=1] language_model.model.layers.47.attention_norm.weight: 50%|█████ | 6/12 [00:00<00:00, 142.96w/s, dev=cpu] language_model.model.layers.47.feed_forward.w2.weight: 58%|█████▊ | 7/12 [00:00<00:00, 165.86w/s, dev=cpu] language_model.model.layers.47.feed_forward.w3.weight: 67%|██████▋ | 8/12 [00:00<00:00, 189.11w/s, dev=cpu] language_model.model.layers.47.ffn_norm.weight: 75%|███████▌ | 9/12 [00:00<00:00, 212.27w/s, dev=cpu]
language_model.model.norm.weight: 83%|████████▎ | 10/12 [00:00<00:00, 235.39w/s, dev=cpu]
language_model.output.weight: 92%|█████████▏| 11/12 [00:00<00:00, 258.51w/s, dev=cpu]

到这就一直卡住，检查了cpu进程，变成僵尸进程了。我是在魔搭下载的模型 5664 root 20 0 0 0 0 Z 0.0 0.0 0:08.23 lmdeploy
5826 root 20 0 0 0 0 Z 0.0 0.0 0:12.25 lmdeploy
6142 root 20 0 0 0 0 Z 0.0 0.0 0:44.71 lmdeploy

Reproduction

部署脚本：

nohup lmdeploy serve api_server /root/data/InternVL2-26B \
--backend turbomind \
--chat-template /root/intervl2/chat_template.json \
--server-port 8001 \
--tp 2 \
>/root/intervl2/log_24.log 2>&1 &

Environment

sys.platform: linux
Python: 3.10.14 (main, Apr  6 2024, 18:45:05) [GCC 9.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3,4,5,6,7: NVIDIA L4
CUDA_HOME: /usr/local/cuda-12.1
NVCC: Cuda compilation tools, release 12.1, V12.1.105
GCC: x86_64-linux-gnu-gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PyTorch: 2.2.2+cu121
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.3.2 (Git Hash 2dc95a2ad0841e29db8b22fbccaf3e5da7992b01)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 12.1
  - 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 8.9.2
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, 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 -DUSE_FBGEMM -DUSE_QNNPACK -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-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -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, PERF_WITH_AVX512=1, TORCH_VERSION=2.2.2, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, 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: 0.17.2+cu121
LMDeploy: 0.5.1+
transformers: 4.43.1
gradio: Not Found
fastapi: 0.111.1
pydantic: 2.8.2
triton: 2.2.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      PIX     SYS     SYS     SYS     SYS     SYS     SYS     96-191  1               N/A
GPU1    PIX      X      SYS     SYS     SYS     SYS     SYS     SYS     96-191  1               N/A
GPU2    SYS     SYS      X      PIX     SYS     SYS     SYS     SYS     96-191  1               N/A
GPU3    SYS     SYS     PIX      X      SYS     SYS     SYS     SYS     96-191  1               N/A
GPU4    SYS     SYS     SYS     SYS      X      PIX     SYS     SYS     96-191  1               N/A
GPU5    SYS     SYS     SYS     SYS     PIX      X      SYS     SYS     96-191  1               N/A
GPU6    SYS     SYS     SYS     SYS     SYS     SYS      X      PIX     96-191  1               N/A
GPU7    SYS     SYS     SYS     SYS     SYS     SYS     PIX      X      96-191  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

No response

InternLM / lmdeploy