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

177 Open 937 Closed
177 Open 937 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

CUDA Setup failed despite GPU being available.
#1559 opened Mar 8, 2025 by dvShilenko
[chore] fix continuous release not working correctly chore
#1558 opened Mar 6, 2025 by Titus-von-Koeller
3 tasks
@Titus-von-Koeller
[spike] evaluate + potentially prototype out-of-tree backend registration spike
#1557 opened Mar 6, 2025 by Titus-von-Koeller
4 tasks
v0.46.0
@Titus-von-Koeller
[spike] evaluate + prototype interaction of unified memory abstraction with custom_ops Optimizers Issues or feature requests relating to optimizers spike
#1556 opened Mar 5, 2025 by Titus-von-Koeller
3 tasks
@Titus-von-Koeller
Increased VRAM consumption when coupled with DDP
#1555 opened Mar 4, 2025 by TParcollet
Custom Ops: Unit Tests cross-platform high priority (first issues that will be worked on)
#1553 opened Mar 3, 2025 by matthewdouglas
5 tasks
v0.46.0
@matthewdouglas
[AMD ROCm] NotImplementedError: bnb_4bit_use_double_quant is not supported yet for CPU/XPU ROCm
#1551 opened Mar 2, 2025 by Looong01 v0.46.0
Improve stack trace when C library does not load contributions-welcome We welcome contributions to fix this issue! Low Risk Risk of bugs in transformers and other libraries medium priority (will be worked on after all high priority issues)
#1548 opened Feb 28, 2025 by matthewdouglas v0.47.0
[RFC] PyTorch Custom Operators & Multi-Backend Support cross-platform high priority (first issues that will be worked on) RFC request for comments on proposed library improvements
#1545 opened Feb 27, 2025 by matthewdouglas v0.46.0
2
non_sign_bits miscalculation in the function 'create_dynamic_map' in bitsandbytes/functional.py high priority (first issues that will be worked on) Low Risk Risk of bugs in transformers and other libraries
#1541 opened Feb 26, 2025 by Talel-bm
1
Wrong result 8bit blockwise quantization over float16 bug Something isn't working high priority (first issues that will be worked on) Low Risk Risk of bugs in transformers and other libraries x64 CPU
#1540 opened Feb 25, 2025 by ZiyueXu77 v0.47.0
2
The main issue seems to be that the main CUDA runtime library was not detected CUDA Setup likely not a BNB issue Linux low priority (will be worked on after all priority issues) Low Risk Risk of bugs in transformers and other libraries question Further information is requested
#1536 opened Feb 21, 2025 by wdh7022
@matthewdouglas
1
Ascend NPU installation Ascend NPU Related to Ascend NPU backend documentation Improvements or additions to documentation Low Risk Risk of bugs in transformers and other libraries
#1523 opened Feb 18, 2025 by LoSunny
1
Multiple issues installing for AMD GPU (Radeon RX7600XT) documentation Improvements or additions to documentation high priority (first issues that will be worked on) Low Risk Risk of bugs in transformers and other libraries ROCm
#1519 opened Feb 16, 2025 by mcondarelli
@matthewdouglas
14
torch.version.cuda.split error bug Something isn't working high priority (first issues that will be worked on) ROCm
#1513 opened Feb 13, 2025 by Lier0 v0.46.0
Default to building the C extension automatically when installing from source build contributions-welcome We welcome contributions to fix this issue! high priority (first issues that will be worked on)
#1511 opened Feb 11, 2025 by mgorny
1
@matthewdouglas
3
The output logistics of Qwen-7B under 8-bit quantization contain NaN proposing to close waiting for info
#1504 opened Feb 9, 2025 by Kairong-Han
2
Cannot load pre-quantized Janus Pro 7B bug Something isn't working medium priority (will be worked on after all high priority issues) Medium risk Risk of bugs in transformers and other libraries
#1498 opened Jan 30, 2025 by neilmehta24
Int8 pipeline parallelism High Risk Risk of bugs in transformers and other libraries medium priority (will be worked on after all high priority issues)
#1482 opened Jan 22, 2025 by psinger
2
Cannot install multi backend (ROCm) Wheel version does not match filename ROCm
#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 proposing to close ROCm
#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
[Ascend][Bug] Fail to use 4-bit quant model to inference Ascend NPU Related to Ascend NPU backend
#1465 opened Dec 28, 2024 by MengqingCao
1
ProTip! Follow long discussions with comments:>50.