Fixes and improvements

• Fix Windows build (#2007) @sssshhhhhh

New features

• Introduce AMD GPU support with ROCm HIP (#1989) @sssshhhhhh
• Compatibility with Transformers v5 (#1999) by @jordimas

Fixes and improvements

• Assume less about whisper vocab (#2000) by @sssshhhhhh
• Use LLVM ThreadSanitizer instead of Google (#1993) by @3manifold
• Optimize all builds with parallel execution (#1992) by @3manifold
• Remove unecessary zero init from conv1d (#1990) by @sssshhhhhh
• Integrate Clang AddressSanitizer in tests (#1903) by @3manifold
• Enable multiple of 16 padding for INT8 Tensor Cores (#1982) by @Purfview
• Add activation and dilation to conv1d (#1979) by @sssshhhhhh
• Minor refactor to CMakeLists.txt (#1980) by @sssshhhhhh
• Remove unnecessary check from wav2vec2 (#1977) by @plan9better
• Add optional residual add to gemm op (#1975) by @sssshhhhhh
• Implement cuda layernorm axis (#1971) by @sssshhhhhh
• Fix Eole conversion (#1998) by @vince62s
• Gemma 3 conversion improvements (#1991) by @sssshhhhhh
• Add causal flag to fa2 (#1976) by @sssshhhhhh
• Fixes cross attention tests and refactors code (#1974) by @jordimas
• Fix CUDA bf16 median filter (#1972) by @sssshhhhhh
• Fix various compiler warnings (#1970) by @sssshhhhhh

v4.6.3 (2026-01-06)

New features

• T5Gemma model conversion and inference (#1962) by @jordimas
• Support for CUDA 12.8 (#1937, #1940) by @Purfview
• Conv1d pure CUDA implementation (#1949), makes cuDNN an optional dependency by @jordimas
• Add CUDA implementation for median filter (#1917) by @ja2d8a4v

Fixes and improvements

• Fix issue- tokens batch_type may exceed max_batch_size (#1948) by @anterart
• Fixes AWQ support for Qwen 2.5/3 and Phi3 (#1951, #1952, #1953) by @BBC-Esq

New features

• Qwen 3 support (#1943) by @jordimas
• Gemma 3 text support (#1936) by @jordimas

Fixes and improvements

• Fixed pkg_resources Deprecated Warning (#1911) by @thawancomt
• Disable INT8 for sm120 - Blackwell GPUs (#1937) by @Purfview
• FIX: package libctranslate2.so in wheel to avoid build fail (#1920) by @yzewei

New features

• Python 3.14 support (#1926)
• Support for Cuda 12.4 (#1925)
• Update Intel oneAPI to version 2025.3 (#1931)

Note: The Ctranslate2 Python package now supports python 3.13, drop the support for python 3.8.

New features

• Pyhton 3.13 support (#1858)
• Support returning hidden vector in Wav2Vec2 and Wav2Vec2Bert Models (#1867)
• Add noexecstack linker flags (#1852 + #1861)
• Support Qwen2 (#1820)
• Eoleconv (#1832)
• Add support RobertModel (#1864)

Fixes and improvements

• Fix github action (#1871)
• Prevent double library def (#1818)

Note: The Ctranslate2 Python package now supports CUDNN 9 and is no longer compatible with CUDNN 8.

New features

• Support Phi3 (#1800)
• Support Mistral Nemo (#1785)
• Support Wav2Vec2Bert ASR (#1778)

Fixes and improvements

• Upgrade to CUDNN9 (#1803)
• Fix logits vocab (#1786 + #1791)
• Update doc AWQ (#1795)

Removed: Flash Attention support in the Python package due to significant package size increase with minimal performance gain.
Note: Flash Attention remains supported in the C++ package with the WITH_FLASH_ATTN option.
Flash Attention may be re-added in the future if substantial improvements are made.

New features

• Support Llama3 (#1751)
• Support Gemma2 (#1772)
• Add log probs for all tokens in vocab (#1755)
• Grouped conv1d (#1749 + #1758)

Fixes and improvements

• Fix pipeline (#1723 + #1747)
• Some improvements in flash attention (#1732)
• Fix crash when using return_alternative on CUDA (#1733)
• Quantization AWQ GEMM + GEMV (#1727)

Note: Because of exceeding project's size on Pypi (> 20 GB), the release v4.3.0 was pushed unsuccessfully.

Fixes and improvements

• Improve the compilation (#1706 and #1705)
• Fix position bias in tensor parallel mode (#1714)

New features

• Support phi-3 (8k and 128k) (#1700 and #1680)

Fixes and improvements

• Fix regression Flash Attention (#1695)