SLIDE | Stockfish | |
---|---|---|
3 | 150 | |
475 | 10,605 | |
-0.4% | 2.3% | |
0.0 | 9.6 | |
over 2 years ago | 4 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
Stockfish
-
Manipulating the Internal World Model of a Chess Playing Language Model
The Stockfish program can be set to play at strength level 0-20. Estimates of the levels' Elo is provided here: https://github.com/official-stockfish/Stockfish/commit/a08b8...
-
A chess terminal user interface implementation
- and handicapped Stockfish (https://stockfishchess.org).
The whole thing is at https://github.com/magv/bchess, and can be installed with just 'pip install bchess'.
- What could I contribute to chess as a developer?
-
posttest-cli beta testers wanted
This was the result searching for all the 35 stockfish benchmark positions to depth 6.
-
How many positions can the top GMs analyze per second? In engine terms what is the highest nps for humans?
Stockfish doesn't have a classical evaluation anymore. And before this, most of the time (around 90%), NNUE was used to evaluate.
-
Stockfish 16 Released +47 Elo gain over Stockfish 15 (Single threaded, UHO)
If you use ChessBase on a MacBook through Parallels, there's an issue where people have posted Apple Silicon compiles for Windows: https://github.com/official-stockfish/Stockfish/issues/4241
-
Stockfish 16 is ready!
Progress can be found here https://github.com/official-stockfish/Stockfish/wiki/Regression-Tests At 1 thread it has gained +18.3 elo on a balanced book, and +47.03 on UHO (unbalanced) book as well as +39.4 elo for FRC and +65.56 for DFRC. At 8 threads it has gained +14.33 elo on a balanced book and +49.46 on UHO (unbalanced book). Also testing was done on 8 threads with 180+1.8 (this is considered very long time control for fishtest standards) and progress was +9.45 on balanced book and +49.65 on UHO.
-
Stockfish 16 is ready
Downloads are available temporarily here https://github.com/official-stockfish/Stockfish/releases/tag/stockfish-dev-20230622-a49b3ba7
-
Is there an engine stronger than Stockfish 15.1?
The strongest version of Stockfish is the latest development version of Stockfish
-
How to integrate Stockfish chess engine into React Native app (for both Android and iOS)
I am trying to implement Stockfish (a popular chess engine) into my React Native app.
What are some alternatives?
YaLM-100B - Pretrained language model with 100B parameters
nibbler - Chess analysis GUI for UCI engines, with extra features for Leela (Lc0) in particular.
lc0 - The rewritten engine, originally for tensorflow. Now all other backends have been ported here.
nnue-pytorch - Stockfish NNUE (Chess evaluation) trainer in Pytorch
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
goslide - SLIDE (Sub-LInear Deep learning Engine) written in Go
fishtest - The Stockfish testing framework
HashingDeepLearning - Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"
maia-chess - Maia is a human-like neural network chess engine trained on millions of human games.
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
Ciphey - ⚡ Automatically decrypt encryptions without knowing the key or cipher, decode encodings, and crack hashes ⚡