Skip to content

Pull requests: bitsandbytes-foundation/bitsandbytes

New pull request New
16 Open 609 Closed
16 Open 609 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix LARS/LAMB optimizer support and non-contiguous tensor handling on XPU Intel Optimizers Issues or feature requests relating to optimizers
#1902 opened Mar 19, 2026 by jiqing-feng Loading… v0.50.0
1
Enable CPU Optimizer Support for bitsandbytes Intel Optimizers Issues or feature requests relating to optimizers x64 CPU
#1901 opened Mar 18, 2026 by jiqing-feng Loading… v0.50.0
3
Update CUDA/ROCm setup tests CUDA Setup CUDA Issues and PRs related to the CUDA backend, excluding installation/support help. ROCm
#1899 opened Mar 13, 2026 by sstamenk Loading… v0.50.0
1
Guard SCB access in Linear8bitLt
#1897 opened Mar 10, 2026 by ailuntz Loading…
1
Allow ROCm arch override
#1896 opened Mar 10, 2026 by ailuntz Loading…
1
3
Replace asserts with errors
#1895 opened Mar 10, 2026 by ailuntz Loading…
1
Clarify Adam8bit arguments
#1894 opened Mar 10, 2026 by ailuntz Loading…
1
[ROCm] Rework ROCm build to use ROCm version instead of HIP version ROCm
#1888 opened Mar 4, 2026 by sstamenk • Draft v0.50.0
5
docs: add quantization and energy efficiency guide Documentation Improvements or additions to documentation
#1882 opened Feb 24, 2026 by hongping-zh Loading…
9
Fix: Linear8bitLt crash with tied weights (skip_modules)
#1865 opened Feb 14, 2026 by TimDettmers Loading…
3 tasks
1
3
fix: Stop quantize_blockwise and quantize_4bit from mutating user-provided absmax
#1863 opened Feb 14, 2026 by TimDettmers Loading…
3 tasks done
1
1
Fix matmul_4bit out parameter not writing to output tensor
#1860 opened Feb 14, 2026 by TimDettmers Loading…
3 of 4 tasks
v0.50.0
1
2
Add k-bit blockwise quantization (K=2-5) with warp-level CUDA kernels CUDA Issues and PRs related to the CUDA backend, excluding installation/support help.
#1858 opened Feb 14, 2026 by TimDettmers Loading…
8
Add MPS backend for Apple Silicon
#1853 opened Jan 31, 2026 by imperatormk Loading…
Renovate pre-commit + CI a bit CI/CD
#1841 opened Jan 14, 2026 by akx • Draft
5
Enable Ascend NPU Backend with Custom Ops Integration for NF4 Support Ascend NPU Related to Ascend NPU backend
#1695 opened Jul 2, 2025 by SlightwindSec Loading…
@matthewdouglas
10
ProTip! Adding no:label will show everything without a label.