Description
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
请问lmdeploy支持k8s方式在昇腾机器上的多节点部署吗，我进行了测试，但是调多节点npu资源失败了，报了以下错误：
yaml文件如下：
apiVersion: apps/v1
kind: Deployment
metadata:
name: npu-deployment
spec:
replicas: 2
selector:
matchLabels:
app: npu-app
strategy: {}
template:
metadata:
labels:
app: npu-app
ascend: "on"
spec:
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
affinity:
podAntiAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
- labelSelector:
matchLabels:
app: npu-app
topologyKey: "kubernetes.io/hostname"
containers:
- name: lmdeploy-container
image: lmdeploy:v0.8.0-ascend-46535327
volumeMounts:
- name: my-storage
mountPath: /nfs
command: ["/bin/bash", "-c", "source /usr/local/Ascend/ascend-toolkit/set_env.sh && source /usr/local/Ascend/nnal/atb/set_env.sh --cxx_abi=0 && lmdeploy serve api_server /nfs/models/Qwen2.5-72B-Instruct --server-port 23333 --device ascend --tp 4"]
env:
- name: LD_LIBRARY_PATH
value: "$LD_LIBRARY_PATH:/usr/local/Ascend/driver/lib64/common/:/usr/local/Ascend/driver/lib64/driver/"
resources:
limits:
huawei.com/Ascend910B: "2"
requests:
huawei.com/Ascend910B: "2"
nodeSelector:
ascend: "on"
volumes:
- name: my-storage
hostPath:
path: /nfs
type: DirectoryReproduction
kubectl apply -f multi_node_lmdeploy.yamlEnvironment
Python: 3.10.5 (main, May 12 2025, 15:01:17) [GCC 9.4.0]
CUDA available: False
MUSA available: False
numpy_random_seed: 2147483648
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
PyTorch: 2.3.1
PyTorch compiling details: PyTorch built with:
- GCC 10.2
- C++ Version: 201703
- 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
- Build settings: BLAS_INFO=open, BUILD_TYPE=Release, CXX_COMPILER=/opt/rh/devtoolset-10/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -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=open, TORCH_VERSION=2.3.1, USE_CUDA=OFF, USE_CUDNN=OFF, USE_CUSPARSELT=OFF, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,
TorchVision: 0.18.1
LMDeploy: 0.8.0+
transformers: 4.51.3
gradio: Not Found
fastapi: 0.115.12
pydantic: 2.11.4
triton: Not FoundError traceback
Metadata
Metadata
Assignees
Labels
No labels