Migrating to BitsAndBytes 0.50.0
Version 0.50.0 introduces 3 breaking changes. This guide details how to update your code.
Released: 7/25/2026
⚠️ Check Your Code
If you use any of these symbols, you need to read this guide:
research moduleblock_wise=False optimizerslegacy dynamic quantization functionsspmm_coospmm_coo_very_sparseigemmbatched_igemmcheck_matmulmatmul_4bitMPS backendgemv_4bitQuantStateParams4bitGlobalOptimManagerLion optimizerBreaking Changes
●Issue #1
Minimum PyTorch version is now 2.4. Users must update PyTorch to at least version 2.4.
●Issue #2
Removed deprecated APIs: the `research` module, non-blockwise (`block_wise=False`) optimizers, and legacy dynamic quantization functions, along with their CUDA/HIP kernels. Code relying on these APIs will need to be updated to use the new blockwise or other supported quantization methods.
●Issue #3
Removed legacy sparse functionality (`spmm_coo`, `spmm_coo_very_sparse`) and dropped the cusparse/hipsparse dependencies. Users of these functions must migrate to alternative sparse matrix multiplication implementations.
Migration Steps
- 1Update PyTorch to at least version 2.4.
- 2Update code that uses the `research` module, non-blockwise (`block_wise=False`) optimizers, or legacy dynamic quantization functions to use supported alternatives.
- 3Migrate from `spmm_coo` and `spmm_coo_very_sparse` to alternative sparse matrix multiplication implementations.
- 4Ensure 4-bit weights passed to `matmul_4bit` are in the `[out_features, in_features]` orientation, not transposed `[in_features, out_features]`.
- 5On macOS 26+, install the `kernels` package for optimal MPS backend performance; otherwise, a naive fallback will be used.
Release Summary
This release introduces significant performance improvements with new fused 4-bit GEMM kernels for inference on CUDA and ROCm, faster CPU operations, and an enhanced Apple Silicon backend. It also brings stability improvements to ROCm support and adds Windows on ARM CPU support.
Need More Details?
View the full release notes and all changes for BitsAndBytes 0.50.0.
View Full Changelog