localai-bot
commented
1 year ago :warning::warning::warning::warning::warning:
Hi! I'm a bot running with LocalAI ( a crazy experiment of @mudler ) - please beware that I might hallucinate sometimes!
_but.... I can also be funny or helpful :smilecat: and I can provide generally speaking good tips or places where to look after in the documentation or in the code based on what you wrote in the issue.
Don't engage in conversation with me, I don't support (yet) replying!
:warning::warning::warning::warning::warning:
Sorry for the issue you are facing while building LocalAI on WSL Ubuntu via VSCode. I can understand that it might be frustrating, but I'll try my best to help you resolve this issue. From the information provided, it seems like there is an error while building the llama.cpp/ggml-cuda.o file during the build process. This could be due to several reasons such as incorrect CMake configuration or missing dependencies. To troubleshoot this issue, you can try the following steps:
- Check if all the required dependencies are installed and up-to-date. You can use the command "sudo apt-get install -y cmake3" to install CMake version 3.27.1 which is the latest version as of now. Additionally, you can check for any missing dependencies by running the command "pip freeze" or "npm list" depending on your project requirements.
- Ensure that the CMake configuration is correct by checking the LocalAI build.sh file and making sure that all the required flags are set correctly. You can also try generating a new CMake cache using the command "cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=/usr/local .." to ensure that the configuration is fresh.
- Check if there are any errors in the build logs by running the command "make VERBOSE=1 BUILD_TYPE=cublas build". This will provide detailed information about the build process and any errors that occur.
- If none of the above steps work, you can try building LocalAI on a different machine or virtual environment to see if the issue persists. I hope this helps! Let me know if you have any further questions or need more assistance.
Sources:
nibiru5
rlleshi
drawsmcgraw
jwalt
dlaliberte
mrbeandev
LocalAI version: 1.22.0
Environment, CPU architecture, OS, and Version: WSL Ubuntu via VSCode Intel x86 i5-10400 Nvidia GTX 1070 Windows 10 21H1
uname -a output: Linux DESKTOP-CU0RN3K 5.10.102.1-microsoft-standard-WSL2 #1 SMP Wed Mar 2 00:30:59 UTC 2022 x86_64 x86_64 x86_64 GNU/Linux
Describe the bug When building on WSL ubuntu, I see this error ... cd build && cp -rf CMakeFiles/ggml.dir/k_quants.c.o ../llama.cpp/k_quants.o cd build && cp -rf CMakeFiles/ggml.dir/ggml-cuda.cu.o ../llama.cpp/ggml-cuda.o cp: cannot stat 'CMakeFiles/ggml.dir/ggml-cuda.cu.o': No such file or directory make[1]: [Makefile:184: llama.cpp/ggml-cuda.o] Error 1 make[1]: Leaving directory '/mnt/d/Projects/AIProjects/LocalAI/LocalAI/go-llama-grammar'make: [Makefile:216: go-llama-grammar/libbinding.a] Error 2
To Reproduce When running this: make BUILD_TYPE=cublas build
It goes perfectly fine until it results in the above error I have attempted make clean, make rebuild, and I unstalled cmake 3.27.1 and golang 1.18.3
Expected behavior It should build successfully without error
Logs Can provide build output if needed...
Additional context I'm less experienced with building on WSL so open to feedback Thank you