Comments (6)
@GuardMoony @aadityabhatia Qigen build is disabled by default now, so you should not face this issue anymore. Feel free to open a PR to fix qigen build, but I don't think many people are using it.
from autogptq.
I believe so. I am using pip
and the files are being downloaded from files.pythonhosted.org
. Here is what I get-
$ pip install -U auto-gptq
Collecting auto-gptq
Using cached auto_gptq-0.7.1.tar.gz (126 kB)
Preparing metadata (setup.py) ... done
Discarding https://files.pythonhosted.org/packages/90/e5/b22697903982284fe284568fb2663a2196694a8eee637f5cf4ccfe435a38/auto_gptq-0.7.1.tar.gz (from https://pypi.org/simple/auto-gptq/) (requires-python:>=3.8.0): Requested auto-gptq from https://files.pythonhosted.org/packages/90/e5/b22697903982284fe284568fb2663a2196694a8eee637f5cf4ccfe435a38/auto_gptq-0.7.1.tar.gz has inconsistent version: expected '0.7.1', but metadata has '0.7.1+cu122'
Using cached auto_gptq-0.7.0.tar.gz (124 kB)
Preparing metadata (setup.py) ... done
Discarding https://files.pythonhosted.org/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz (from https://pypi.org/simple/auto-gptq/) (requires-python:>=3.8.0): Requested auto-gptq from https://files.pythonhosted.org/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz has inconsistent version: expected '0.7.0', but metadata has '0.7.0+cu122'
Downloading auto_gptq-0.6.0.tar.gz (120 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 121.0/121.0 kB 1.7 MB/s eta 0:00:00
from autogptq.
Same issue here. Why not just use multiprocessing.cpu_count()
or os.cpu_count()
to count the CPUs?
from autogptq.
Thank you! Was able to install directly from github: pip install git+https://github.com/AutoGPTQ/AutoGPTQ
Part of the issue was also an issue with versioning: auto_gptq-0.7.0.tar.gz has inconsistent version: expected '0.7.0', but metadata has '0.7.0+cu122
, which caused pip to use older versions.
Collecting auto-gptq
Using cached auto_gptq-0.7.0.tar.gz (124 kB) Preparing metadata (setup.py) ... done Discarding https://files.pythonhosted.org/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz (from https://pypi.org/simple/auto-gptq/) (requires-python:>=3.8.0): Requested auto-gptq from https://files.pythonhosted.org/packages/34/71/c3e73cf17681f6ff4754ef8f4cb8b67af3def230fc8711eac1250bbd78d5/auto_gptq-0.7.0.tar.gz has inconsistent version: expected '0.7.0', but metadata has '0.7.0+cu122'
Using cached auto_gptq-0.6.0.tar.gz (120 kB)
Preparing metadata (setup.py) ... done
Discarding https://files.pythonhosted.org/packages/49/af/02b66e55dfd9aeb0ece923843043724ed7432ec0c649ea0f3b9fa1dd90c6/auto_gptq-0.6.0.tar.gz (from https://pypi.org/simple/auto-gptq/) (requires-python:>=3.8.0): Requested auto-gptq from https://files.pythonhosted.org/packages/49/af/02b66e55dfd9aeb0ece923843043724ed7432ec0c649ea0f3b9fa1dd90c6/auto_gptq-0.6.0.tar.gz has inconsistent version: expected '0.6.0', but metadata has '0.6.0+cu122'
Using cached auto_gptq-0.5.1.tar.gz (112 kB)
from autogptq.
Verified. It's working correctly now.
from autogptq.
Part of the issue was also an issue with versioning: auto_gptq-0.7.0.tar.gz has inconsistent version: expected '0.7.0', but metadata has '0.7.0+cu122, which caused pip to use older versions.
Is this on pypi?
from autogptq.
Related Issues (20)
- [DEPRECATION] Discussion on Fused attention and QiGEN HOT 5
- Llama-3 8B Instruct quantized to 8 Bit spits out gibberish in transformers `model.generate()` but works fine in vLLM? HOT 5
- [BUG]safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
- [Question] Differences in quantization logic compared to AWQ
- [FEATURE] ADD SUPPORT DeepSeek-V2 HOT 1
- [BUG] ARM installation error
- [BUG] ROCm installation and building broken
- Target modules [] not found in the base model. Please check the target modules and try again.
- [BUG] Cannot install from source
- [BUG] Following the quant_with_alpaca.py example but keep getting "You shouldn't move a model that is dispatched using accelerate hooks." and the model is never saved. HOT 2
- [FEATURE] Models that support MOE do GPTQ
- [FEATURE] Add marlin24 support
- How to select between different kernels?
- Question about data shape difference between quantization and forward
- [FEATURE] Added code support to 5,6,7 bits quantization can you please add me as contributor I will create a new pull request HOT 4
- [BUG] Quantitative model Yi-1.5-9b-16K does not produce text output.
- How to install auto-gptq in GCC 8.5.0 environment?
- How to get a dequantized model?
- [BUG] Not able to install on Ubuntu 22.04 (subprocess-exited-with-error ) HOT 2
- [BUG]
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 autogptq.