TalkChess.com

Good to know!

Again thanks for testing.

Daniel

Thanks for testing Scorpio!

Did you use uci or winboard mode for Scorpio ? I discovered a bug in winboard mode relating time controls
using fractions as you do, with 60+0.6. It will think the increment is 0 instead of 0.6.
This bug is not present in UCI mode though.

Daniel

I have added something that could be the cause of that. When one side is winning by 90 percent or more only one of the winning variations is searched. This inflates winning scores and is able to find mates better than previous version. But the first two games against defenchess probably due to end g...

Hi Jamal, The new graphics cards 3080 require new versions of cuda (11.1) and cudnn 8. The default installation of Scorpio like you did will not work on a 3080 because that is compiled with cuda 10. Cudnn 8 is more than 1 GB in size so I don't ship that. If you have cuda 11 and cudnn 8 already insta...

I already have half the number of weights in the input layer by taking advantage of vertical symmetry.
But that doesn't decrease the inference time unlike your ff-0.5 idea.
Who knows a NNUE eval that is faster than classic could result in a better engine.

I wouldn't say search is obsolete now because it is very hard to write a search as efficient as stockfish's. If it was that easy, other engines like komodo would have done it before NNs arrived to the scene. That is why I think treating stockfish search as a "net runner" is plain wrong. The proof is...

An observation: playing around with the Scorpio 3.0.11 settings, I noticed that using NNUEs doesn't make it necessary to use Scorpio egbbs. An example: -using 5-men egbb loaded into the RAM memory-82% -using only 3 & 4-men loaded into the RAM memory-91% The rest of the conditions were identical. I ...

I set mt=1 in the ini file but Scorpio still uses 2 cores of my 4-core engine. What shall I do? Hi Gabor, What mode are you running ? It should obey mt parameter for NNUE/HCE but the meaning of the mt parameter is different for NNs. Please don't change the mt parameter in that case. If you have a G...

Training a NNUE net from A0 style res nets, such as an Lc0 net, is not new either. Dkappe already trained several nets with this approach, and often his nets require different scaling than SF style nets. I see it as a ripoff of the latest and greatest open source project with some bizarre claims of...

https://de.chessbase.com/post/fat-fritz-2-0-die-neue-nummer-1 Commercial version of SF? I smell SF dev here :) . Not really. I am testing Fat Fritz 2 right now. Fat Fritz 2 uses a nnue net, which is 2x bigger, than the Stockfish nnue-nets. Because of this, the binary is more than 40MB in size and t...