Update bitsandbytes requirement from >=0.50.0 to >=0.50.2

[dependabot]

Updates the requirements on bitsandbytes to permit the latest version.

Release notes

Sourced from bitsandbytes's releases.

0.50.2

Highlights

• ROCm 10.0 build is now included for both Linux and Windows.
• Additional AMD GPU targets are included in our prebuilt wheels.
• Performance improvement for certain 4bit GEMM shapes on NVIDIA GB10.

What's Changed

• Mask the absmax store in the Triton 4-bit quantize kernels by @​truong-v in bitsandbytes-foundation/bitsandbytes#2043
• Add sm121 (GB10) to the wide_n_simt 4-bit GEMM dispatch rule by @​yashb98 in bitsandbytes-foundation/bitsandbytes#2039
• chore(deps): bump the actions group across 1 directory with 2 updates by @​dependabot[bot] in bitsandbytes-foundation/bitsandbytes#2036
• [ROCm] Harden HIP version for native library naming and selection by @​sstamenk in bitsandbytes-foundation/bitsandbytes#1888
• Revert "[ROCm] Harden HIP version for native library naming and selection" by @​matthewdouglas in bitsandbytes-foundation/bitsandbytes#2060
• [ROCm] Restore Wave64 warp size for all gfx9 targets by @​0xDELUXA in bitsandbytes-foundation/bitsandbytes#2059
• ci: expand ROCm architecture coverage by @​sstamenk in bitsandbytes-foundation/bitsandbytes#2046
• [ROCm] Add CI for ROCm 10.0 by @​sstamenk in bitsandbytes-foundation/bitsandbytes#2061

New Contributors

• @​truong-v made their first contribution in bitsandbytes-foundation/bitsandbytes#2043
• @​0xDELUXA made their first contribution in bitsandbytes-foundation/bitsandbytes#2059

Full Changelog: bitsandbytes-foundation/bitsandbytes@0.50.1...0.50.2

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

0.44.1

Bug fixes:

... (truncated)

Commits

• 08a9956 Release 0.50.2
• 4f1fc6c [ROCm] Add CI for ROCm 10.0 (#2061)
• 906ff4d ci: expand ROCm architecture coverage (#2046)
• d9e4440 Restore Wave64 warp size for all gfx9 targets (#2059)
• 3fe95b5 Revert "[ROCm] Rework ROCm build to use ROCm version instead of HIP version (...
• 3ac90c4 [ROCm] Rework ROCm build to use ROCm version instead of HIP version (#1888)
• 95f9af3 chore(deps): bump the actions group across 1 directory with 2 updates (#2036)
• d2d08f6 Add sm121 (GB10) to the wide_n_simt 4-bit GEMM dispatch rule (#2039)
• d8ccdd9 Mask the absmax store in the Triton 4-bit quantize kernels (#2043)
• 2b6cfb7 Bump dev version
• Additional commits viewable in compare view