Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CPP build failed with errors #2949

Closed
chauhang opened this issue Feb 19, 2024 · 0 comments · Fixed by #2953
Closed

CPP build failed with errors #2949

chauhang opened this issue Feb 19, 2024 · 0 comments · Fixed by #2953
Assignees
Labels
bug Something isn't working c++ internal Issues found internally
Milestone

Comments

@chauhang
Copy link
Contributor

chauhang commented Feb 19, 2024

🐛 Describe the bug

Testing the cpp build on AWS g5.8xlarge failed with error while building Sentencepiece dependecy: make: *** No rule to make target '32'. Stop.

Further it installed CPU version of the libtorch even after using the install steps:

python ts_scripts/install_dependencies.py --cpp --cuda=cu118
cd cpp
./build.sh

Error logs

Full details here

Installation instructions

Install steps

python ts_scripts/install_dependencies.py --cpp --cuda=cu118
cd cpp
./build.sh

Model Packaing

Failed before reaching this step

config.properties

No response

Versions


Environment headers

Torchserve branch:

**Warning: torchserve not installed ..
**Warning: torch-model-archiver not installed ..

Python version: 3.8 (64-bit runtime)
Python executable: /usr/bin/python3

Versions of relevant python libraries:
captum==0.6.0
numpy==1.24.3
nvgpu==0.10.0
pillow==10.2.0
psutil==5.9.5
requests==2.31.0
requests-unixsocket==0.2.0
torch==2.2.0+cu118
torchaudio==2.2.0+cu118
torchdata==0.7.1
torchtext==0.17.0+cpu
torchvision==0.17.0+cu118
wheel==0.42.0
torch==2.2.0+cu118
torchtext==0.17.0+cpu
torchvision==0.17.0+cu118
torchaudio==2.2.0+cu118

Java Version:

OS: Ubuntu 20.04.6 LTS
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: N/A
CMake version: version 3.26.3

Is CUDA available: Yes
CUDA runtime version: 11.8.89
GPU models and configuration:
GPU 0: NVIDIA A10G
Nvidia driver version: 525.85.12
cuDNN version: None

Repro instructions

Failed during build of cpp

python ts_scripts/install_dependencies.py --cpp --cuda=cu118
cd cpp
./build.sh

Possible Solution

No response

@chauhang chauhang added bug Something isn't working c++ internal Issues found internally labels Feb 19, 2024
@mreso mreso mentioned this issue Feb 21, 2024
3 tasks
@chauhang chauhang added this to the v0.10.0 milestone Feb 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working c++ internal Issues found internally
Projects
Status: Done
Development

Successfully merging a pull request may close this issue.

2 participants