Comments (3)
numSearchThreads is the number of CPU threads to use. If your GPU is powerful, it can actually be much higher than the number of CPU cores on your system because you will need many threads in order to feed large enough batches to the GPU to get good GPU use.
nnMaxBatchSize should be be around the number of CPU threads you are using, yes, but how large it needs to be can vary if you are using multiple GPUs instead of 1 GPU.
You will want to use cudaUseFP16 and cudaUseNHWC if your GPU has FP16 tensor cores.
If you are doing long searches with large numbers of visits, and you don't mind using more RAM on your machine, nnCacheSizePowerOfTwo can be increased, and also nnMutexPoolSizePowerOfTwo. I think the config comes with nnCacheSizePowerOfTwo = 18 meaning that it will cache 2^18 = 262144 neural net results, but due to birthday paradox you may start getting some noticeable cache losses once you start searching in the high thousands of visits.
Thanks for the question, hope that helps. I'll add some more documentation about various parameters to the README or otherwise within the release itself before too long, I just haven't done it yet.
from katago.
Thank you very much.
from katago.
from katago.
Related Issues (20)
- Will Finetuned 9x9 Neural Net continue to be trained and updated? HOT 2
- How to get the whiteOwnerMap of the current board state? HOT 4
- Log best move and score changes at specific evaluation thresholds? HOT 1
- Why is katago on an 11 way board, where the thread count only goes up to 60 max, and then it doesn't analyze when it's cranked up further
- The allowMoves is invalid. HOT 1
- I have doubts about the analysis results with 6x6 HOT 2
- about "v15" model format HOT 1
- About CUDA version and TRT version of 1.14.0 HOT 4
- KataGo Dockerfile for Raspberry Pi 4
- The latest version of tensorrt can't be loaded successfully, can 28b be sent in advance, I want to test HOT 7
- Why can't the katago engine set the 355 mesh and how to solve this problem?
- TENSORRT compiling error with latest code HOT 7
- Can't run katago 1.14 on Ubuntu 22.04 missing libzip.so.5 HOT 2
- Whoever can compile the latest 1.14 tensorrt and send me the latest 28b, I'll test it HOT 3
- Running b28 reports an error, I don't know what is wrong with the 1.14 engine HOT 1
- 1.14 What are the new configuration parameters that can be set between the engine and the previous engine?
- katago 1.14.0 TRT plan cache boots significantly slower than 1.13.2 HOT 8
- engines freezes intermittently while using katago1.14(with lizzieyzy) HOT 1
- Proposal for Docker Integration to Test KataGo Versions Across Various Environments HOT 2
- report: v1.13.2-kata9x9
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from katago.