Comments (7)
Not sure about Fedora but in Arch you need to install gcc11 which can coexist with the gcc12 that is already installed.
pacman -S gcc11
Then type this in the console you're about to install GPTQ:
export CC=gcc-11 CXX=g++-11
followed by
python setup_cuda.py install
from gptq-for-llama.
Update:
Solved by installing g++ through Conda:
conda install -c conda-forge gxx
from gptq-for-llama.
Not sure about Fedora but in Arch you need to install gcc11 which can coexist with the gcc12 that is already installed.
pacman -S gcc11
Then type this in the console you're about to install GPTQ:
export CC=gcc-11 CXX=g++-11
followed by
python setup_cuda.py install
Thank you, it seems that it's not possible to install previous gcc versions on Fedora anymore (At least not from the official repos). But the answer should be good for Ubuntu and Arch users
from gptq-for-llama.
Update: Solved by installing g++ through Conda:
conda install -c conda-forge gxx
I'm using Fedora. I tried this and it still doesn't work.
from gptq-for-llama.
Update: Solved by installing g++ through Conda:
conda install -c conda-forge gxx
I'm using Fedora. I tried this and it still doesn't work.
I've also installed conda install gcc_linux-64==11.2.0
, probably both are needed.
You might need to deactivate and reactivate the Conda environment.
I'm running Nobara which ships with official Nvidia Gpu & Cuda drivers, as the kmod kernel is needed to use Nvidia/Cuda, if you don't have it, you might have to install it through rpmfusion
from gptq-for-llama.
Not sure about Fedora but in Arch you need to install gcc11 which can coexist with the gcc12 that is already installed.
pacman -S gcc11
Then type this in the console you're about to install GPTQ:
export CC=gcc-11 CXX=g++-11
followed by
python setup_cuda.py install
Well this got me one step forward, but now the install is erroring out with 'cannot find -lcudart'
"...
/usr/bin/ld: cannot find -lcudart: No such file or directory
collect2: error: ld returned 1 exit status
error: command '/usr/bin/g++-11' failed with exit code 1""
Is this a package I could just copy/paste from somewhere to that directory, or do I need to solve this some other way?
Edit: I was missing CUDA, stupidly. Everything working now.
from gptq-for-llama.
I have Fedora 38 too.
conda install -c conda-forge gcc_linux-64==11.2.0 gxx_linux-64==11.2.0
export PATH=${PATH}:${HOME}/.conda/envs/textgen/bin/
export CC=x86_64-conda-linux-gnu-gcc CXX=x86_64-conda-linux-gnu-g++
replace textgen by your conda env.
from gptq-for-llama.
Related Issues (20)
- llama_inference 4bits error
- inference with the saved model error: AttributeError: module 'torch.backends.cuda' has no attribute 'sdp_kernel' HOT 2
- Could not obtain official perplexity using bloom_eval()
- can it support openllama model?
- Issue with GPTQ HOT 1
- High PPL when groupsize != -1 for OPT model after replace linear layer with quantlinear. HOT 1
- Help: Quantized llama-7b model with custom prompt format produces only gibberish HOT 1
- Why does the model quantization prompt KILLED at the end? HOT 2
- Would GPTQ be able to support LLaMa2? HOT 1
- Can i quantize HF version of llama model
- Transformers broke again (AttributeError: 'GPTQ' object has no attribute 'inp1') HOT 1
- LoRa and diff with bitsandbytes
- neox.py needs to add "import math"
- error: block with no terminator, has llvm.cond_br %5624, ^bb2, ^bb3
- Support Mistral.
- Syntax changed in triton.testing.do_bench() causing error when running llama_inference.py
- datasets.utils.info_utils.ExpectedMoreSplits: {'validation'} HOT 1
- Error when load GPTQ model
- GPTQ vs bitsandbytes
- add support for minicpm
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gptq-for-llama.