Skip to content

Issues: bitsandbytes-foundation/bitsandbytes

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.

Sign up for GitHub

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

180 Open 834 Closed
180 Open 834 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Paged optimizer resuming from checkpoint - attributeError: 'int' object has no attribute 'cpu'
#1381 opened Oct 1, 2024 by shivam15s
Release v44 not available for Mac
#1378 opened Sep 30, 2024 by ACMCMC
2
Model architecture is modified when I use BitsAndBytesConfig with default params
#1371 opened Sep 25, 2024 by yunhao-tech
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling cublasGemmEx
#1363 opened Sep 17, 2024 by LukeLIN-web
1
Merge LoRA into 405B
#1359 opened Sep 16, 2024 by junzhang-zj
4
cuda is available but import bnb error
#1355 opened Sep 13, 2024 by ZeroneBo
2
Model not able to quantize
#1354 opened Sep 12, 2024 by alielfilali01
Bug when using optimizer LAMB 32bits bug Something isn't working
#1350 opened Sep 5, 2024 by FrsECM
Torch autograd support for dequantize methods
#1347 opened Sep 4, 2024 by yaldashbz
Cannot load decoder.lm_head.weight when loading 4 bit quantized model using VisionEncoderDecoder.from_pretrained
#1343 opened Aug 30, 2024 by AditiJain14
1
quantize_4bit/dequantize_4bit gives wrong output on in-contiguous tensor
#1342 opened Aug 30, 2024 by chenqianfzh
Linear8bitLt can not be moved back to cpu bug Something isn't working
#1332 opened Aug 24, 2024 by Nerogar
Pretrained Causal LM cannot be loaded in 4bit/8bit likely not a BNB issue
#1331 opened Aug 23, 2024 by adrienchaton
6
Any plan to support block size 32? enhancement New feature or request
#1329 opened Aug 20, 2024 by lllyasviel
4
RuntimeError: Failed to import transformers.integrations.bitsandbytes because of the following error (look up to see its traceback):
#1327 opened Aug 20, 2024 by pradeep10kumar
1
RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information:
#1322 opened Aug 18, 2024 by pradeep10kumar
1
'nf4' compute datatype? question Further information is requested
#1321 opened Aug 15, 2024 by dorsa-zeinali
1
where are the outliers stored in LLM.int8 quantization for inference suing transformers library on AMD GPU?
#1320 opened Aug 15, 2024 by vbayanag
1
About fusion of **kdequantize kernel** and **simple bf16/fp16 matmul**
#1319 opened Aug 15, 2024 by Ther-nullptr
1
Communicate blocksize constraints to kernels that take blocksize as a runtime argument enhancement New feature or request Low Risk Risk of bugs in transformers and other libraries
#1317 opened Aug 14, 2024 by mm04926412
@matthewdouglas
6
Unable to override PyTorch CUDA Version CUDA Setup waiting for info
#1315 opened Aug 13, 2024 by tinglvv
4
4bit quantized model.dequantize() fails on CPU
#1311 opened Aug 7, 2024 by npbool
RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information: python -m bitsandbytes Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues
#1307 opened Aug 6, 2024 by senzawapoi
Regarding bnb import error waiting for info
#1306 opened Aug 6, 2024 by Mubashirshariq
@matthewdouglas
2
bitsbytes 8bit quantized LLama 3.1 gets stuck sometimes when producing output
#1304 opened Aug 5, 2024 by Techbhatia
ProTip! Follow long discussions with comments:>50.