[Bug] internvl3-8b cannot be quantized on 3090.

### 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

internvl3-8b cannot be quantized on 3090.

### Reproduction

lmdeploy lite auto_awq /nvme/qa_test_models/OpenGVLab/InternVL3-8B --work-dir /nvme/qa_test_models/OpenGVLab/InternVL3-8B-inner-4bits --batch-size 8

### 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: NVIDIA GeForce RTX 3090
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.4, V12.4.131
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
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: 0.8.0+c0f91af
transformers: 4.51.3
gradio: 5.29.0
fastapi: 0.115.12
pydantic: 2.11.4
triton: 3.2.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-35 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

```Shell
E AssertionError: Token indices sequence length is longer than the specified maximum sequence length for this model (1104485 > 12288). Running this sequence through the model will result in indexing errors
E Traceback (most recent call last):
E File "/opt/py3/bin/lmdeploy", line 8, in
E sys.exit(run())
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/cli/entrypoint.py", line 39, in run
E args.run(args)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/cli/lite.py", line 111, in auto_awq
E auto_awq(**kwargs)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/apis/auto_awq.py", line 87, in auto_awq
E vl_model, model, tokenizer, work_dir = calibrate(model,
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/apis/calibrate.py", line 315, in calibrate
E calib_ctx.calibrate(all_data)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/quantization/calibration.py", line 224, in calibrate
E _ = model(data.to(self.device))
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
E return self._call_impl(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
E return forward_call(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/transformers/utils/generic.py", line 965, in wrapper
E output = func(self, *args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 549, in forward
E layer_outputs = decoder_layer(
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
E return self._call_impl(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
E return forward_call(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/quantization/calibration.py", line 152, in _forward
E batch_outputs.append(self._ori_forwards[mod](*batch_args[i], **batch_kwargs[i]))
E File "/opt/py3/lib/python3.10/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 262, in forward
E hidden_states, self_attn_weights = self.self_attn(
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
E return self._call_impl(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
E return forward_call(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 207, in forward
E attn_output = self.o_proj(attn_output)
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
E return self._call_impl(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1845, in _call_impl
E return inner()
E File "/opt/py3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1782, in inner
E args_result = hook(self, args)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/quantization/calibration.py", line 113, in _input_hook
E obs.observe(inp[0])
E File "/opt/py3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
E return func(*args, **kwargs)
E File "/opt/py3/lib/python3.10/site-packages/lmdeploy/lite/quantization/activation/observer.py", line 96, in observe
E assert torch.isnan(x).sum() == 0
```