[Bug] CUDA runtime error: operation not supported /lmdeploy/src/turbomind/utils/allocator.h:197

[JingMo]

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

RuntimeError: [TM][ERROR] CUDA runtime error: operation not supported /lmdeploy/src/turbomind/utils/allocator.h:197

Reproduction

lmdeploy serve api_server --model-name internlm/internlm2_5-7b-chat --server-port 23333

from https://huggingface.co/internlm/internlm2-chat-7b

Environment

sys.platform: linux
Python: 3.10.14 (main, May  6 2024, 19:42:50) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: GRID A100D-3-40C MIG 3g.40gb
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.2, V12.2.91
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.3.1+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 v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: NO AVX
  - 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=2.3.1, 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: 0.18.1+cu121
LMDeploy: 0.5.3+
transformers: 4.41.0
gradio: 4.42.0
fastapi: 0.112.2
pydantic: 2.8.2
triton: 2.3.1
NVIDIA Topology: 
        GPU0    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     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

Error traceback

2024-09-02 14:34:00,529 - lmdeploy - INFO - updated backend_config=TurbomindEngineConfig(model_name=None, model_format=None, tp=1, session_len=None, max_batch_size=128, cache_max_entry_count=0.8, cache_block_seq_len=64, enable_prefix_caching=False, quant_policy=0, rope_scaling_factor=0.0, use_logn_attn=False, download_dir=None, revision=None, max_prefill_token_num=8192, num_tokens_per_iter=0, max_prefill_iters=1)
[TM][DEBUG] Set logger level by DEBUG
[TM][DEBUG] turbomind::Allocator<turbomind::AllocatorType::CUDA>::Allocator(int, bool)
Traceback (most recent call last):
  File "/data01/MindSearch/l.py", line 2, in <module>
    pipe = lmdeploy.pipeline("internlm/internlm2_5-7b-chat", log_level='DEBUG')
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/site-packages/lmdeploy/api.py", line 89, in pipeline
    return pipeline_class(model_path,
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 218, in __init__
    self.gens_set.add(self.engine.create_instance())
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 356, in create_instance
    return TurboMindInstance(self, cuda_stream_id)
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 388, in __init__
    future.result()
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/concurrent/futures/_base.py", line 458, in result
    return self.__get_result()
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
    raise self._exception
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "/data01/miniconda3/envs/mindsearch2/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 397, in _create_model_instance
    model_inst = self.tm_model.model_comm.create_model_instance(
RuntimeError: [TM][ERROR] CUDA runtime error: operation not supported /lmdeploy/src/turbomind/utils/allocator.h:197