Bump bitsandbytes from 0.44.1 to 0.48.2

[dependabot]

Bumps bitsandbytes from 0.44.1 to 0.48.2.

Release notes

Sourced from bitsandbytes's releases.

0.48.2

What's Changed

• Fix indexing overflow issue for blockwise quantization by @​matthewdouglas in bitsandbytes-foundation/bitsandbytes#1784
• Fix regression with CPU/disk offloading for accelerate + int8 by @​matthewdouglas in bitsandbytes-foundation/bitsandbytes#1786
• XPU: Add Windows build for SYCL kernels by @​matthewdouglas in bitsandbytes-foundation/bitsandbytes#1787

Full Changelog: bitsandbytes-foundation/bitsandbytes@0.48.1...0.48.2

0.48.1

This release fixes a regression introduced in 0.48.0 related to LLM.int8(). This issue caused poor inference results with pre-quantized checkpoints in HF transformers.

What's Changed

• Add trove-classifiers requirement to pyproject.toml by @​ccoulombe in bitsandbytes-foundation/bitsandbytes#1774
• Fix regression in 8bit parameter device movement by @​matthewdouglas in bitsandbytes-foundation/bitsandbytes#1776

Full Changelog: bitsandbytes-foundation/bitsandbytes@0.48.0...0.48.1

0.48.0: Intel GPU & Gaudi support, CUDA 13, performance improvements, and more!

Highlights

🎉 Intel GPU Support

We now officially support Intel GPUs on Linux and Windows! Support is included for all major features (LLM.int8(), QLoRA, 8bit optimizers) with the exception of the paged optimizer feature.

This support includes the following hardware:

• Intel® Arc™ B-Series Graphics
• Intel® Arc™ A-Series Graphics
• Intel® Data Center GPU Max Series

A compatible PyTorch version with Intel XPU support is required. The current minimum is PyTorch 2.6.0. It is recommended to use the latest stable release. See Getting Started on Intel GPU for guidance.

🎉 Intel Gaudi Support

We now officially support Intel Gaudi2 and Gaudi3 accelerators. This support includes LLM.int8() and QLoRA with the NF4 data type. At this time optimizers are not implemented.

A compatible PyTorch version with Intel Gaudi support is required. The current minimum is Gaudi v1.21 with PyTorch 2.6.0. It is recommended to use the latest stable release. See the Gaudi software installation guide for guidance.

NVIDIA CUDA

• The 4bit dequantization kernel was improved by @​Mhmd-Hisham in #1746. This change brings noticeable speed improvements for prefill, batch token generation, and training. The improvement is particularly prominent on A100, H100, and B200.
• We've added CUDA 13.0 compatibility across Linux x86-64, Linux aarch64, and Windows x86-64 platforms.
  • Hardware support for CUDA 13.0 is limited to Turing generation and newer.
  • Support for Thor (SM110) is available in the Linux aarch64 build.

🚨 Breaking Changes

• Dropped support for PyTorch 2.2. The new minimum requirement is 2.3.0.
• Removed Maxwell GPU support for all CUDA builds.

What's Changed

• add py.typed by @​cyyever in bitsandbytes-foundation/bitsandbytes#1726
• Enable F841 by @​cyyever in bitsandbytes-foundation/bitsandbytes#1727

... (truncated)

Changelog

Sourced from bitsandbytes's changelog.

v0.45.1

Improvements:

• Compatibility for triton>=3.2.0
• Moved package configuration to pyproject.toml
• Build system: initial support for NVIDIA Blackwell B100 GPUs, RTX 50 Blackwell series GPUs and Jetson Thor Blackwell.
  • Note: Binaries built for these platforms are not included in this release. They will be included in future releases upon the availability of the upcoming CUDA Toolkit 12.7 and 12.8.

Bug Fixes:

• Packaging: wheels will no longer include unit tests. (#1478)

Dependencies:

• Sets the minimum PyTorch version to 2.0.0.

0.45.0

This is a significant release, bringing support for LLM.int8() to NVIDIA Hopper GPUs such as the H100.

As part of the compatibility enhancements, we've rebuilt much of the LLM.int8() code in order to simplify for future compatibility and maintenance. We no longer use the col32 or architecture-specific tensor layout formats while maintaining backwards compatibility. We additionally bring performance improvements targeted for inference scenarios.

Performance Improvements

This release includes broad performance improvements for a wide variety of inference scenarios. See this X thread for a detailed explanation.

Breaking Changes

🤗PEFT users wishing to merge adapters with 8-bit weights will need to upgrade to peft>=0.14.0.

Packaging Improvements

• The size of our wheel has been reduced by ~43.5% from 122.4 MB to 69.1 MB! This results in an on-disk size decrease from ~396MB to ~224MB.
• Binaries built with CUDA Toolkit 12.6.2 are now included in the PyPI distribution.
• The CUDA 12.5.0 build has been updated to CUDA Toolkit 12.5.1.

Deprecations

• A number of public API functions have been marked for deprecation and will emit FutureWarning when used. These functions will become unavailable in future releases. This should have minimal impact on most end-users.
• The k-bit quantization features are deprecated in favor of blockwise quantization. For all optimizers, using block_wise=False is not recommended and support will be removed in a future release.
• As part of the refactoring process, we've implemented many new 8bit operations. These operations no longer use specialized data layouts.

Full Changelog

• refine docs for multi-backend alpha release by @​Titus-von-Koeller in #1380
• README: Replace special Unicode text symbols with regular characters by @​akx in #1385
• Update CI tools & fix typos by @​akx in #1386
• Fix invalid escape sequence warning in Python 3.12 by @​oshiteku in #1420
• [Build] Add CUDA 12.6.2 build; update 12.5.0 to 12.5.1 by @​matthewdouglas in #1431
• LLM.int8() Refactoring: Part 1 by @​matthewdouglas in #1401

Commits

• b48ecdb Release 0.48.2
• fd9934c XPU: Add Windows build for SYCL kernels (#1787)
• 9029e36 Fix regression with CPU/disk offloading for accelerate + int8 (#1786)
• 34400d2 Fix indexing overflow issue for blockwise quantization with large tensor size...
• c3b8de2 Bump dev version
• 7e16503 Patch Release 0.48.1
• 874111f Fix regression in 8bit parameter device movement (#1776)
• f48050f Add trove-classifiers requirement to pyproject.toml (#1774)
• 00c0a1a Bump dev version
• 406fb6a Fix Release 0.48.0
• Additional commits viewable in compare view

You can trigger a rebase of this PR by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

[dependabot]

Superseded by #507.