| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| rocm-python-wheels-Linux.zip | 2026-11-02 | 390.4 MB | |
| rocm-python-wheels-Windows.zip | 2026-11-02 | 159.0 MB | |
| README.md | 2026-11-02 | 1.3 kB | |
| v4.8.5 source code.tar.gz | 2026-11-02 | 3.6 MB | |
| v4.8.5 source code.zip | 2026-11-02 | 3.9 MB | |
| Totals: 5 Items | 556.9 MB | 0 | |
New features
- Cache Drama 3 prompt prefixes with LRU eviction, cache controls, and hit/miss diagnostics (#2133, [#2144]) by @jordimas
- Add native CPU reference-audio encoding for Drama 3 voice cloning (#2141) by @jordimas
Fixes and improvements
- Preserve FP32 attention scores through softmax to fix CUDA alignment precision with FP16 and BF16 models (#2143) by @jordimas
- Improve Drama 3 prefill performance by increasing the default chunk size from 16 to 128, and fuse gated-delta projections during GPU decoding (#2133) by @jordimas
- Fix caching allocator shutdown crashes when the allocating thread exits (#2136) by @jordimas
- Fix FP16 overflow in CUDA attention score accumulation (#2131) by @jordimas
- Fix the eole converter scale for relative position keys (#2138) by @maksimcialehin
- Add a Windows ROCm/HIP build guide and document AMD GPU support (#2041) by T0nd3 and @jordimas
- Add CUDA build instructions for NVIDIA Jetson devices (#2019) by @vimalk78
