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

223 Open 873 Closed
223 Open 873 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

help me
#1533 opened Feb 20, 2025 by huhuba
ImportError: Requires latest bitsandbytes despite already being installed (Colab)
#1530 opened Feb 20, 2025 by vatsalparikh07
Blockwise quantization only supports 16/32-bit floats, but got torch.uint8
#1525 opened Feb 19, 2025 by nitinmukesh
FileNotFoundError: Could not find module 'C:\aitest\SkyReels-V1\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.dll'
#1524 opened Feb 19, 2025 by nitinmukesh
1
Ascend NPU installation Ascend NPU Related to Ascend NPU backend
#1523 opened Feb 18, 2025 by LoSunny
1
question
#1522 opened Feb 18, 2025 by mc-xm
Multiple issues installing for AMD GPU (Radeon RX7600XT) AMD integration documentation Improvements or additions to documentation
#1519 opened Feb 16, 2025 by mcondarelli
@matthewdouglas
3
Required library version not found: libbitsandbytes_cuda124_nocublaslt.so CUDA Setup Linux question Further information is requested
#1518 opened Feb 15, 2025 by MostHumble
4
Rtx 5090 & Getting Error Using 8bit Adam Optimizer
#1517 opened Feb 15, 2025 by faruknane
The confusion surrounding bnb_4bit_compute_dtype, torch_dtype, and prepare_model_for_kbit_training.
#1515 opened Feb 14, 2025 by xiaobingbuhuitou
Cuda 12.6 Windows 11. Can't find GPU
#1514 opened Feb 13, 2025 by vlegacy
1
torch.version.cuda.split error AMD integration bug Something isn't working
#1513 opened Feb 13, 2025 by Lier0
Default to building the C extension automatically when installing from source build contributions-welcome We welcome contributions to fix this issue!
#1511 opened Feb 11, 2025 by mgorny
1
@matthewdouglas
3
libbitsandbytes_cuda128.dll file does not exist Windows
#1510 opened Feb 11, 2025 by tripleS-Dev
3
Version error by building from source build
#1509 opened Feb 11, 2025 by jiqing-feng
1
The output logistics of Qwen-7B under 8-bit quantization contain NaN
#1504 opened Feb 9, 2025 by Kairong-Han
1
Cannot load pre-quantized Janus Pro 7B
#1498 opened Jan 30, 2025 by neilmehta24
No module named 'triton.ops' with new triton versions due to removed triton.ops.matmul_perf_model code duplicate This issue or pull request already exists
#1492 opened Jan 25, 2025 by lamikr
4
训练出错，cuda缺少libcusparse.so.11，更新重装都没用，请大佬帮忙看看，感谢
#1483 opened Jan 23, 2025 by sgg-comeon
Int8 pipeline parallelism
#1482 opened Jan 22, 2025 by psinger
Cannot install multi backend (ROCm) Wheel version does not match filename AMD integration
#1473 opened Jan 9, 2025 by RSWilli
2
asking for CUDA 124 when only CUDA 126 exists CUDA Setup
#1470 opened Jan 7, 2025 by ron0studios
[BUG] AMD GPU compilation from source AMD integration
#1468 opened Jan 4, 2025 by krenax
8
AttributeError: 'NoneType' object has no attribute 'cquantize_blockwise_fp16_fp4'
#1467 opened Jan 3, 2025 by hessaAlawwad
i am trying to install forge UI but its getting stuck at this CUDA Setup
#1466 opened Jan 1, 2025 by MetaYousuf
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.