[Bug] MiniCPM-V-2_6 and InternVL2_5-26B are not supported when communicator='native'. Is that expected?

### 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

MiniCPM-V-2_6 and InternVL2_5-26B are not supported when communicator='native'. Is that expected?

### Reproduction

lmdeploy chat openbmb/MiniCPM-V-2_6 --tp 2 --communicator native

### Environment

```Shell
sys.platform: linux
Python: 3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.5.1+cu118
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 11.8
- 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_37,code=sm_37;-gencode;arch=compute_90,code=sm_90
- CuDNN 90.1
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, 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+cu118
LMDeploy: 0.7.2.post1+422c3b1
transformers: 4.49.0
gradio: 5.19.0
fastapi: 0.115.8
pydantic: 2.10.6
triton: 3.1.0
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 CPU Affinity NUMA Affinity
GPU0 X NV12 NV12 NV12 NV12 NV12 NV12 NV12 0-27,56-83 0
GPU1 NV12 X NV12 NV12 NV12 NV12 NV12 NV12 0-27,56-83 0
GPU2 NV12 NV12 X NV12 NV12 NV12 NV12 NV12 0-27,56-83 0
GPU3 NV12 NV12 NV12 X NV12 NV12 NV12 NV12 0-27,56-83 0
GPU4 NV12 NV12 NV12 NV12 X NV12 NV12 NV12 28-55,84-111 1
GPU5 NV12 NV12 NV12 NV12 NV12 X NV12 NV12 28-55,84-111 1
GPU6 NV12 NV12 NV12 NV12 NV12 NV12 X NV12 28-55,84-111 1
GPU7 NV12 NV12 NV12 NV12 NV12 NV12 NV12 X 28-55,84-111 1

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
root@6e0879b660a8:/__w/lmdeploy/lmdeploy# CUDA_VISIBLE_DEVICES=2,3 lmdeploy chat openbmb/MiniCPM-V-2_6 --tp 2 --communicator native
chat_template_config:
ChatTemplateConfig(model_name='minicpmv-2d6', system=None, meta_instruction=None, eosys=None, user=None, eoh=None, assistant=None, eoa=None, tool=None, eotool=None, separator=None, capability='chat', stop_words=None)
engine_cfg:
TurbomindEngineConfig(dtype='auto', model_format=None, tp=2, dp=1, device_num=None, attn_tp_size=None, attn_dp_size=None, mlp_tp_size=None, mlp_dp_size=None, outer_dp_size=None, session_len=32768, max_batch_size=1, 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='native')
[WARNING] gemm_config.in is not found; using default GEMM algo
[WARNING] gemm_config.in is not found; using default GEMM algo

double enter to end input >>> nihao

<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
nihao<|im_end|>
<|im_start|>assistant
[TM][ERROR] [Engine] not implemented
Aborted (core dumped)
```