LC0 Chess Engines

LC0 (Leela Zero) Chess Engines.....Legendary...."A Engine Whose DNA was Firmly Established when Alpha Zero Played and Supposedly Defeated Stockfish v8.0 in a 100 game match some years ago (Opinions Vary On the Validity Of That Match" However Human Players Were Fascinated That A Non-Stockfish Based Engine Could Compete with and Actually Defeat The Strongest Chess Engine In The World....'STOCKFISH" A engine with a completely different playing style and different hardware and scanning process for the move generation..."Human Like Style" "Positional Attacker" "Zugswang Genius" Leela Zero is Based On Alpha Zero Concepts"

"New visible features v0.17.0 (Early Version)

Implemented ponder support.

Tablebases are supported now (only WDL probe for now).
Command line parameter is
--syzygy-paths=/path/to/syzygy/

Old smart pruning flag is gone. Instead there is --futile-search-aversion flag.
--futile-search-aversion=0 is equivalent to old --no-smart-pruning.
--futile-search-aversion=1 is equivalent to old --smart-pruning.
Now default is 1.47, which means that engine will sometimes decide to stop search earlier even when there is theoretical chance (but not very probable) that best move decision could be changed if allowed to think more.

Lc0 now supports configuration files. Options can be listed there instead of
command line flags / uci params.
Config should be named lc0.config and located in the same directory as lc0.
Should list one command line option per line, with '--' in the beginning being optional, for example:

syzygy-paths=/path/to/syzygy/

In uci info, "depth" is now average depth rather than full depth (which was 4 all the time).
Also, depth values do not include reused tree, only nodes visited during the current search session.

--sticky-checkmates experimental flag (default off), supposed to find shorter checkmate sequences.

More features in backend "check".

Performance optimizations

Release windows executables are built with "whole program optimization".
Added --out-of-order-eval flag (default is off).
Switching it on makes cached/terminal nodes higher priority, which increases nps.
OpenCL backend now supports batches (up to 5x speedup!)
Performance optimizations for BLAS backend.
Total visited policy (for FPU reduction) is now cached.
Values of priors (P) are stored now as 16-bit float rather than 32-bit float, that saves considerable amount of RAM."


LC0 Development #2387 (Git) Appeveyor

https://ci.appveyor.com/api/buildjobs
/dx08urxuaqc27pxh/artifacts/build%2Flc0.exe

LC0 v0.30.0 (Blas)

https://github.com/LeelaChessZero/lc0/releases/download/v0.30.0/lc0-v0.30.0-windows-cpu-openblas.zip

LC0 v0.29.0 (Blas)

https://github.com/LeelaChessZero/lc0/releases/download/v0.29.0/lc0-v0.29.0-windows-cpu-openblas.zip

LC0 v0.28.0 (Blas)

https://github.com/LeelaChessZero/lc0/releases/download/v0.28.0/lc0-v0.28.0-windows-cpu-openblas.zip

LC0 v0.27.0 (Blas)

https://github.com/LeelaChessZero/lc0/releases/download/v0.27.0/lc0-v0.27.0-windows-cpu-openblas.zip

LC0 Best Nets Link......

https://lczero.org/dev/wiki/best-nets-for-lc0/

Lc0 BT4 Development...."vBT4:
Big transformer 4. New network architecture which builds off of BT3 by adding two types of auxiliary heads, future heads and categorical value heads. The categorical value heads predict a distribution over values of q rather than a WDL outcome distribution, and the future heads predict the moves that will be played over the next two plies. The hope is that these heads will give additional information to the net to improve training speed. We've also fixed half-precision training, so this model will be larger. BT4 training started in mid-October and is expected to take a few months. It has 15 layers with 1024 embedding size, 32 heads per layer, and 1536 emb size, for roughly a doubling in size over BT3."


BT4 Dev

https://katfile.com/t8mh3dxxdkuz/LC0_BT4.7z.html


https://pixeldrain.com/u/QQqUZUxM