[Bug] A100单卡40G执行lmdeploy报错Aborted (core dumped)

### 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

执行命令：
lmdeploy serve api_server /root/autodl-tmp/llava-1.5-7b-hf --server-port 23333 --log-level DEBUG

具体日志：
2025-04-23 16:40:12,211 - lmdeploy - INFO - builder.py:65 - matching vision model: LlavaHfVisionModel
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2025-04-23 16:40:18,558 - lmdeploy - INFO - async_engine.py:259 - input backend=turbomind, backend_config=TurbomindEngineConfig(dtype='auto', model_format=None, tp=1, session_len=None, max_batch_size=256, cache_max_entry_count=0.8, cache_chunk_size=-1, 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, communicator='nccl')
2025-04-23 16:40:18,559 - lmdeploy - INFO - async_engine.py:260 - input chat_template_config=None
2025-04-23 16:40:18,564 - lmdeploy - INFO - async_engine.py:269 - updated chat_template_onfig=ChatTemplateConfig(model_name='llava-v1', system=None, meta_instruction=None, eosys=None, user=None, eoh=None, assistant=None, eoa=None, tool=None, eotool=None, separator=None, capability=None, stop_words=None)
2025-04-23 16:40:18,730 - lmdeploy - INFO - turbomind.py:279 - model_source: ModelSource.HF_MODEL
2025-04-23 16:40:18,790 - lmdeploy - INFO - turbomind.py:187 - turbomind model config:

{
"model_config": {
"model_name": "",
"chat_template": "",
"model_arch": "LlavaForConditionalGeneration",
"head_num": 32,
"kv_head_num": 32,
"hidden_units": 4096,
"vocab_size": 32064,
"embedding_size": 32064,
"num_layer": 32,
"inter_size": [
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008,
11008
],
"norm_eps": 1e-05,
"attn_bias": 0,
"qk_norm": false,
"size_per_head": 128,
"group_size": 64,
"weight_type": "float16",
"session_len": 4096,
"tp": 1,
"model_format": "hf",
"expert_num": [],
"expert_inter_size": 0,
"experts_per_token": 0,
"moe_shared_gate": false,
"norm_topk_prob": false,
"routed_scale": 1.0,
"topk_group": 1,
"topk_method": "greedy",
"moe_group_num": 1,
"q_lora_rank": 0,
"kv_lora_rank": 0,
"qk_rope_dim": 0,
"v_head_dim": 0,
"tune_layer_num": 1
},
"attention_config": {
"rotary_embedding": 128,
"rope_theta": 10000.0,
"softmax_scale": 0.0,
"attention_factor": null,
"max_position_embeddings": 4096,
"original_max_position_embeddings": 0,
"rope_scaling_type": "",
"rope_scaling_factor": 0.0,
"use_dynamic_ntk": 0,
"low_freq_factor": 1.0,
"high_freq_factor": 1.0,
"beta_fast": 32.0,
"beta_slow": 1.0,
"use_logn_attn": 0,
"cache_block_seq_len": 64
},
"lora_config": {
"lora_policy": "",
"lora_r": 0,
"lora_scale": 0.0,
"lora_max_wo_r": 0,
"lora_rank_pattern": "",
"lora_scale_pattern": ""
},
"engine_config": {
"dtype": "auto",
"model_format": null,
"tp": 1,
"session_len": null,
"max_batch_size": 256,
"cache_max_entry_count": 0.8,
"cache_chunk_size": -1,
"cache_block_seq_len": 64,
"enable_prefix_caching": false,
"quant_policy": 0,
"rope_scaling_factor": 0.0,
"use_logn_attn": false,
"download_dir": null,
"revision": null,
"max_prefill_token_num": 8192,
"num_tokens_per_iter": 8192,
"max_prefill_iters": 1,
"communicator": "nccl"
}
}
[TM][DEBUG] Set logger level by DEBUG
[TM][WARNING] [LlamaTritonModel] `max_context_token_num` is not set, default to 4096.
[TM][INFO] Model:
head_num: 32
kv_head_num: 32
size_per_head: 128
num_layer: 32
vocab_size: 32064
attn_bias: 0
qk_norm: 0
max_batch_size: 256
max_prefill_token_num: 8192
max_context_token_num: 4096
num_tokens_per_iter: 8192
max_prefill_iters: 1
session_len: 4096
cache_max_entry_count: 0.8
cache_block_seq_len: 64
cache_chunk_size: -1
enable_prefix_caching: 0
tensor_para_size: 1
pipeline_para_size: 1
enable_custom_all_reduce: 0
model_name:
model_dir:
quant_policy: 0
group_size: 64
expert_per_token: 0
moe_method: 1

[TM][DEBUG] Set logger level by DEBUG
[TM][INFO] TM_FUSE_SILU_ACT=1
Aborted (core dumped)
root@autodl-container-00ff4cb9d9-a7b255f7:~/autodl-tmp#

### Reproduction

执行命令：
lmdeploy serve api_server /root/autodl-tmp/llava-1.5-7b-hf --server-port 23333 --log-level DEBUG

### Environment

```Shell
环境检查：
check_env
sys.platform: linux
Python: 3.12.3 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:46:43) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA A100-PCIE-40GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.4, V12.4.131
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: 0.7.3+
transformers: 4.51.3
gradio: 5.25.2
fastapi: 0.115.12
pydantic: 2.11.3
triton: 3.1.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-79 0-1 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

```Shell

```