InternVL icon indicating copy to clipboard operation
InternVL copied to clipboard
Published 3 months ago • verified publisher icon OpenGVLab

[Bug] 关于推理InternVL3-78B权重的时候出现SafetensorError异常

Open CalcuLuUus opened this issue 8 months ago • 0 comments

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

无论是使用lmdeploy还是vllm对InternVL3-78B进行推理的时候均会触发SafetensorError异常: Error while deserializing header: HeaderTooLarge，但是使用InternVL3-78B-Instruct就没事

Reproduction

以下是使用AI辅写的检测代码，其中safetensors为最新版

import os
from safetensors.torch import safe_open
from safetensors import SafetensorError

# 你要扫描的文件夹路径
safetensors_dir = "InternVL3-78B"

def scan_safetensors_files(directory):
    files = [f for f in os.listdir(directory) if f.endswith('.safetensors')]
    if not files:
        print("❌ 没找到任何 .safetensors 文件")
        return

    print(f"🔍 开始扫描 {len(files)} 个 safetensors 文件...\n")

    for filename in sorted(files):
        filepath = os.path.join(directory, filename)
        try:
            with open(filepath, "rb") as f_raw:
                # Safetensors header 是放在文件最开头的
                header_len_bytes = int.from_bytes(f_raw.read(8), "little")
            
            header_size_kb = header_len_bytes / 1024

            with safe_open(filepath, framework="pt") as f:
                metadata = f.metadata()
                num_tensors = len(f.keys())

            print(f"✅ {filename} 正常 | header 大小: {header_size_kb:.2f} KB | tensors数量: {num_tensors}")

        except SafetensorError as e:
            print(f"❌ {filename} SafetensorError异常: {e}")
        except Exception as e:
            print(f"❌ {filename} 其他异常: {e}")

if __name__ == "__main__":
    scan_safetensors_files(safetensors_dir)

该代码的输出为：

🔍 开始扫描 33 个 safetensors 文件...

✅ model-00001-of-00033.safetensors 正常 | header 大小: 31.09 KB | tensors数量: 269
✅ model-00002-of-00033.safetensors 正常 | header 大小: 30.45 KB | tensors数量: 262
✅ model-00003-of-00033.safetensors 正常 | header 大小: 8.04 KB | tensors数量: 68
❌ model-00004-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00005-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00006-of-00033.safetensors 正常 | header 大小: 3.68 KB | tensors数量: 29
❌ model-00007-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00008-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
❌ model-00009-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00010-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00011-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00012-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
✅ model-00013-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
✅ model-00014-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00015-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00016-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00017-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00018-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00019-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00020-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
✅ model-00021-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
✅ model-00022-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00023-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00024-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00025-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00026-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00027-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00028-of-00033.safetensors 正常 | header 大小: 4.46 KB | tensors数量: 35
❌ model-00029-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
✅ model-00030-of-00033.safetensors 正常 | header 大小: 3.70 KB | tensors数量: 29
❌ model-00031-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00032-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge
❌ model-00033-of-00033.safetensors SafetensorError异常: Error while deserializing header: HeaderTooLarge

Environment

sys.platform: linux
Python: 3.10.15 (main, Oct  3 2024, 07:27:34) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3: NVIDIA H20
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.4, V12.4.131
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PyTorch: 2.6.0+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, COMMIT_SHA=2236df1770800ffea5697b11b0bb0d910b2e59e1, 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=2.6.0, 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: 0.21.0+cu124
LMDeploy: 0.7.3+869d3be
transformers: 4.52.0.dev0
gradio: Not Found
fastapi: 0.115.12
pydantic: 2.11.3
triton: 3.2.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5    NIC6    NIC7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV18    NV18    NV18    PIX     NODE    NODE    NODE    SYS     SYS     SYS     SYS     0-47    0               N/A
GPU1    NV18     X      NV18    NV18    NODE    NODE    NODE    PIX     SYS     SYS     SYS     SYS     0-47    0               N/A
GPU2    NV18    NV18     X      NV18    SYS     SYS     SYS     SYS     NODE    PIX     NODE    NODE    48-84   1               N/A
GPU3    NV18    NV18    NV18     X      SYS     SYS     SYS     SYS     NODE    NODE    NODE    PIX     48-84   1               N/A
NIC0    PIX     NODE    SYS     SYS      X      NODE    NODE    NODE    SYS     SYS     SYS     SYS
NIC1    NODE    NODE    SYS     SYS     NODE     X      NODE    NODE    SYS     SYS     SYS     SYS
NIC2    NODE    NODE    SYS     SYS     NODE    NODE     X      NODE    SYS     SYS     SYS     SYS
NIC3    NODE    PIX     SYS     SYS     NODE    NODE    NODE     X      SYS     SYS     SYS     SYS
NIC4    SYS     SYS     NODE    NODE    SYS     SYS     SYS     SYS      X      NODE    NODE    NODE
NIC5    SYS     SYS     PIX     NODE    SYS     SYS     SYS     SYS     NODE     X      NODE    NODE
NIC6    SYS     SYS     NODE    NODE    SYS     SYS     SYS     SYS     NODE    NODE     X      NODE
NIC7    SYS     SYS     NODE    PIX     SYS     SYS     SYS     SYS     NODE    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_1
  NIC1: mlx5_2
  NIC2: mlx5_3
  NIC3: mlx5_4
  NIC4: mlx5_5
  NIC5: mlx5_6
  NIC6: mlx5_7
  NIC7: mlx5_8

Error traceback

CalcuLuUus avatar Apr 28 '25 02:04 CalcuLuUus