[Bug] InternVL3-78B produces incorrect / unstable inference results on A800 with TurboMind backend (works correctly on V100)

[niuwagege]

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

When running InternVL3-78B inference on an A800 (SM80) server using lmdeploy + TurboMind backend, the model produces incorrect and unstable outputs, including:

• Empty responses ("")
• Repetitive sentences
• Semantically meaningless text

The same model, code, and prompts work correctly on an 8×V100 (SM70) server, producing stable and reasonable outputs.

This suggests a potential TurboMind / SM80 (Ampere) specific issue, possibly related to attention kernels, KV cache, or numerical precision.

result from A800:
TheAsAsAsAsTheAsAsAsTheAsTheTheTheTheTheTheTheTheAsTheTheAsTheAsTheAsAsAsAsTheAsTheAsAsAsAsAsAsAsAsAsAsAsAsAsAsAsTheTheAsTheAsAsAsAsAsAsAsTheTheAsTheTheThe

Reproduction

from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/InternVL3-78B'
image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=16384, tp=8), chat_template_config=ChatTemplateConfig(model_name='internvl3'))
response = pipe(('describe this image', image))
print(response.text)

Environment

sys.platform: linux
Python: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3,4,5,6,7: NVIDIA A800-SXM4-80GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.8, V12.8.61
GCC: gcc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
PyTorch: 2.8.0+cu128
PyTorch compiling details: PyTorch built with:
  - GCC 13.3
  - 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 v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 12.8
  - NVCC architecture flags: -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;-gencode;arch=compute_100,code=sm_100;-gencode;arch=compute_120,code=sm_120
  - CuDNN 91.0.2  (built against CUDA 12.9)
    - Built with CuDNN 90.8
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=a1cb3cc05d46d198467bebbb6e8fba50a325d4e7, CUDA_VERSION=12.8, CUDNN_VERSION=9.8.0, CXX_COMPILER=/opt/rh/gcc-toolset-13/root/usr/bin/c++, CXX_FLAGS= -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 -DC10_NODEPRECATED -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-dangling-reference -Wno-error=dangling-reference -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.8.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=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, USE_XCCL=OFF, USE_XPU=OFF, 

TorchVision: 0.23.0+cu128
LMDeploy: 0.11.1+
transformers: 4.57.1
fastapi: 0.121.1
pydantic: 2.11.10
triton: 3.4.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    NIC1    NIC2    NIC3    NIC4    NIC5  NIC6     NIC7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV8     NV8     NV8     NV8     NV8     NV8     NV8     PIX     PIX     NODE    NODE    SYS     SYS   SYS      SYS     0-61    0               N/A
GPU1    NV8      X      NV8     NV8     NV8     NV8     NV8     NV8     PIX     PIX     NODE    NODE    SYS     SYS   SYS      SYS     0-61    0               N/A
GPU2    NV8     NV8      X      NV8     NV8     NV8     NV8     NV8     NODE    NODE    PIX     PIX     SYS     SYS   SYS      SYS     0-61    0               N/A
GPU3    NV8     NV8     NV8      X      NV8     NV8     NV8     NV8     NODE    NODE    PIX     PIX     SYS     SYS   SYS      SYS     0-61    0               N/A
GPU4    NV8     NV8     NV8     NV8      X      NV8     NV8     NV8     SYS     SYS     SYS     SYS     PIX     PIX   NODE     NODE    62-123  1               N/A
GPU5    NV8     NV8     NV8     NV8     NV8      X      NV8     NV8     SYS     SYS     SYS     SYS     PIX     PIX   NODE     NODE    62-123  1               N/A
GPU6    NV8     NV8     NV8     NV8     NV8     NV8      X      NV8     SYS     SYS     SYS     SYS     NODE    NODE  PIX      PIX     62-123  1               N/A
GPU7    NV8     NV8     NV8     NV8     NV8     NV8     NV8      X      SYS     SYS     SYS     SYS     NODE    NODE  PIX      PIX     62-123  1               N/A
NIC0    PIX     PIX     NODE    NODE    SYS     SYS     SYS     SYS      X      PIX     NODE    NODE    SYS     SYS   SYS      SYS
NIC1    PIX     PIX     NODE    NODE    SYS     SYS     SYS     SYS     PIX      X      NODE    NODE    SYS     SYS   SYS      SYS
NIC2    NODE    NODE    PIX     PIX     SYS     SYS     SYS     SYS     NODE    NODE     X      PIX     SYS     SYS   SYS      SYS
NIC3    NODE    NODE    PIX     PIX     SYS     SYS     SYS     SYS     NODE    NODE    PIX      X      SYS     SYS   SYS      SYS
NIC4    SYS     SYS     SYS     SYS     PIX     PIX     NODE    NODE    SYS     SYS     SYS     SYS      X      PIX   NODE     NODE
NIC5    SYS     SYS     SYS     SYS     PIX     PIX     NODE    NODE    SYS     SYS     SYS     SYS     PIX      X    NODE     NODE
NIC6    SYS     SYS     SYS     SYS     NODE    NODE    PIX     PIX     SYS     SYS     SYS     SYS     NODE    NODE   X       PIX
NIC7    SYS     SYS     SYS     SYS     NODE    NODE    PIX     PIX     SYS     SYS     SYS     SYS     NODE    NODE  PIX       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_bond_0
  NIC1: mlx5_bond_1
  NIC2: mlx5_bond_2
  NIC3: mlx5_bond_3
  NIC4: mlx5_bond_4
  NIC5: mlx5_bond_5
  NIC6: mlx5_bond_6
  NIC7: mlx5_bond_7

Error traceback

[lvhan028]

Hi, this is a member from LMDeploy team. We will handle this issue and keep posting update under issue InternLM/lmdeploy#4285