Comments (3)
Hi @qxpBlog,
bitsandbytes
is not currently built with support for aarch64 platforms. Releases prior to 0.43.0 to PyPI were tagged as supporting all platforms, but moving forward the wheels are tagged appropriately for the platforms they support. As of right now, that is just Windows and Linux on x86-64.
You can follow #997 for more information on plans to support additional platforms.
from bitsandbytes.
嗨,
bitsandbytes
当前不支持 aarch64 平台。PyPI 的 0.43.0 之前的版本被标记为支持所有平台,但今后轮子会针对它们支持的平台进行适当的标记。截至目前,这只是 x86-64 上的 Windows 和 Linux。您可以关注 #997 以获取有关支持其他平台的计划的更多信息。
thanks for your help.
from bitsandbytes.
I had the same issue of bitandbytes 0.42.0 being available, but not 0.43+ on RHEL 7 (centOS 7 and other older distros should also be affected):
The pip release of bitsandbytes 0.43.0+ requires glibc 0.24+, while some older distros don't have it. You can verify by running: ldd --version
If you run into this issue, you can either use the conda-forge instead (supports glibc 2.17+) or build from source.
from bitsandbytes.
Related Issues (20)
- NameError: name 'str2optimizer32bit' is not defined HOT 2
- torch compile support? HOT 1
- 32 bit optimizer update error despite gradients being the same HOT 4
- Quantized model using load_in_8bit produces very different results on T4 vs V100 GPU on Colab
- NameError: name 'str2optimizer32bit' is not defined HOT 1
- CUDA Setup failed despite CUDA being Available :: NameError: name 'str2optimizer32bit' is not defined HOT 4
- bitsandbytes interprets URLs from environment variables as paths HOT 2
- Bug issues
- error on VectorstoreIndexCreator HOT 6
- CONTRIBUTING.md references Meta CLA HOT 1
- bitsandbytes import error in colab HOT 1
- Could not run Kohya
- PicklingError: Can't pickle <function Embedding.forward at XXXXXXX> it's not the same object as torch.nn.modules.sparse.Embedding.forward
- AttributeError: 'NoneType' object has no attribute 'split' CUDA Setup failed despite CUDA being available.
- Mistral-v0.1 nf4 is not quantized into 4bit HOT 1
- RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information: HOT 3
- problem with loading my finetuned Llama2 model - type object 'Params4bit' has no attribute 'from_prequantized' HOT 3
- undefined symbol: cdequantize_blockwise_fp32 HOT 1
- AnimateDiff SDXL won't run
- AttributeError: 'NoneType' object has no attribute 'cquantize_blockwise_fp16_nf4' HOT 5
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 bitsandbytes.