List view

<code>bitsandbytes.functional.quantize_4bit</code>, <code>bitsandbytes.functional.quantize_blockwise</code> require contiguous input, fail silently if not

Status: Open.

Bug

#1690 In bitsandbytes-foundation/bitsandbytes;

· mseeger opened on Jun 29, 2025

Percentile Clipping causes FutureWarning

Contributions WelcomeWe welcome contributions to fix this issue!We welcome contributions to fix this issue!

DocumentationImprovements or additions to documentationImprovements or additions to documentation

OptimizersIssues or feature requests relating to optimizersIssues or feature requests relating to optimizers

Status: Open.

#1713 In bitsandbytes-foundation/bitsandbytes;

· Avelina9X opened on Jul 19, 2025

quantize_blockwise (CPU) occurs Segmentation fault when all block elements are zero

x64 CPU

Status: Open.

Bug

#1744 In bitsandbytes-foundation/bitsandbytes;

· im0qianqian opened on Sep 2, 2025

Reduce CUDA build matrix

Build

CUDAIssues and PRs related to the CUDA backend, excluding installation/support help.Issues and PRs related to the CUDA backend, excluding installation/support help.

Status: Open.

Task

#1778 In bitsandbytes-foundation/bitsandbytes;

· matthewdouglas opened on Oct 3, 2025

Support quantizing tensors when numel() &gt; INT_MAX

CUDAIssues and PRs related to the CUDA backend, excluding installation/support help.Issues and PRs related to the CUDA backend, excluding installation/support help.

Status: Open.

Feature

#1785 In bitsandbytes-foundation/bitsandbytes;

· matthewdouglas opened on Oct 22, 2025

Compatibility when torch.compile is not supported

torch.compile

Status: Open.

Bug

#1813 In bitsandbytes-foundation/bitsandbytes;

· matthewdouglas opened on Nov 26, 2025