Finally, the first v0.30.0 release candidate is out. You can find it in <
https://github.com/LeelaChessZero/lc0/releases/tag/v0.30.0-rc1>. There are still a few pending changes before the final release, so a second release candidate will be out soon, but as they do not affect core functionality we made this pre-release to make support for attention body networks more easily available. The main features of this release are:
* Support for networks with attention body and smolgen added to blas, cuda, metal and onnx backends.
* Persistent L2 cache optimization for the cuda backend. Use the `cache_opt=true` backend option to turn it on.
* Some performance improvements for the cuda, onnx and blas backends.
* Added the `threads` backend option to onnx, defaults to 0 (let the onnxruntime decide) except for onnx-cpu that defaults to 1.
* The onnx-dml package now includes a `directml.dll` installation script.
* Some users experienced memory issues with onnx-dml, so the defaults were changed. This may affect performance, in which case you can use the `steps=8` backend option to get the old behavior.
* The Python bindings are available as a package, see the README for instructions.
* Some assorted fixes and code cleanups.