SLIDE
lc0
SLIDE | lc0 | |
---|---|---|
3 | 12 | |
475 | 2,330 | |
-0.4% | 1.5% | |
0.0 | 8.7 | |
over 2 years ago | 5 days ago | |
C++ | ||
- | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
SLIDE
-
Yandex opensources 100B parameter GPT-like model
That's pretty much what SLIDE [0] does. The driver was achieving performance parity with GPUs for CPU training, but presumably the same could apply to running inference on models too large to load into consumer GPU memory.
https://github.com/RUSH-LAB/SLIDE
- [R] CPU algorithm trains deep neural nets up to 15 times faster than top GPU trainers
- CPU-based algorithm trains deep neural nets up to 15 times faster than top GPU
lc0
-
How the Lc0 Training Games Work (In Windows)
So according to the Releases page at https://github.com/LeelaChessZero/lc0/releases on the 1st of January 2022, Lc0 was in version 0.28.2. That takes care of the [White ""] and [Black ""] headers. To get the ratings, I went to the CCRL and looked it up: https://ccrl.chessdom.com/ccrl/404/cgi/compare_engines.cgi?family=Leela%20Chess
-
Leela Chess Zero v0.29.0 has been released!
Lc0 0.29.0 - released - A beautiful gift for Mac users. (chessengeria.com) Release v0.29.0 · LeelaChessZero/lc0 (github.com)
-
Setting up Maia chess locally and making it play unique games
Sorry, I should've said it in a more clear way. The feature isn't broken in general, but it wasn't intended to be used for randomizing move selection by policy value (normally it uses number of visits, if I understand correctly). This was changed in this PR so I don't think there's any issue that needs to be reported.
-
FM Dennis Monokroussos' Open Letter to Ken Regan + Regan's response
UCI is designed to interface with GUIs. He needs it to be usable in "batch mode" which means providing input games/files on a command-line. I just looked at the lc0 documentation. There doesn't seem to be any way of integrating a batch mode https://github.com/LeelaChessZero/lc0/blob/master/FLAGS.md
- Stockfish 15 Eval(x-axis) to Leela Eval(y-axis) Graph
-
Can you find the only winning move for White?
If you are curious where this game is from, this is actually a computer chess game that I ran on my machine between Leela Chess Zero 0.29.0 prerelease on https://github.com/LeelaChessZero/lc0/releases (CUDNN) playing with the black pieces, and Stockfish 22060708 64X BMI2 on https://abrok.eu/stockfish playing with the white pieces. The game continued 17. Bxe6 Kxe6 18. f4 Nxf4 19. Qg4+ Kd5 20. Rxf4 gxf4. If you check that position with Stockfish 15 NNUE on chess.com, it should realize that it is winning.
-
TIL no human has beaten a computer in a chess tournament in over 15 years
For example: https://github.com/LeelaChessZero/lc0/wiki/Contributing-Training-Games
- Silent chip swap in GTX1650 cards craters performance
-
What's a simple engine to modify? (Preferably in Python)
I suspect in a PUCTS based engine, simply changing the parameters to make the search wider could have the effect you want. Ie, the engine will try losing moves more often, which reduces the expected value of a node if it doesn't have a lot of similar options. I haven't checked Leela out in a while, but there is a good chance you don't even need to modify code to try that. https://github.com/LeelaChessZero/lc0
- CPU-based algorithm trains deep neural nets up to 15 times faster than top GPU
What are some alternatives?
YaLM-100B - Pretrained language model with 100B parameters
Stockfish - A free and strong UCI chess engine
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
maia-chess - Maia is a human-like neural network chess engine trained on millions of human games.
goslide - SLIDE (Sub-LInear Deep learning Engine) written in Go
Koivisto - UCI Chess engine
HashingDeepLearning - Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"
nnue-pytorch - Stockfish NNUE (Chess evaluation) trainer in Pytorch
cutechess - Cute Chess is a graphical user interface, command-line interface and a library for playing chess.
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
secondchess - secondchess is a chess engine by Emilio Díaz, based on firstchess by Pham Hong Nguyen