I have a very big, 4k screen and two rtx 2080 ti gpus.

Do I need Leela Zero 0.17 + AutoGTP v18?
https://github.com/leela-zero/leela-zero/releases

It also looks like both gpus were using ~68% of gpu load.
I thought it should be something like 90% or more?

At the beginning, when I run analyse mode without doing any moves, I see: visits per second are between 5000 and 30000.
Shouldn't it be somehow stable?

After 4000000 playouts, the visits are very low between 2000 and 5000.
Why?

How the stop Lizzie from automatically stop analysis?
I want to use the full potential of my powerful hardware, I have 64 GB memory.

Can Lizzie/Leela use a mirrow technique?
This would increase the strength and also use the ressources and time more efficiently.
(4 moves) For example, if D4 have 1.5m visits and 43,2 evaluation, then Q16, Q4 and D16 should automatically get the same visits and evaluation (like copy and paste without analysis).
(8 moves) When 6th best move is C4 with 250k visits and 43,1 evaluation, then D3, R16, Q17, R4, Q3, C16 and D17 should automatically get the same visits and evaluation.
Instead of analysing 8 moves, it would be enough to analyse one move, so we will need only 1/8 of our time to get the same result in this case.
The 7/8 of our time must be used to analyse the other different moves and to analyse deeper.

Lizzie stoped after 18347638 playouts automatically.
Looks like 99.99% from the analysis goes to the 12 moves, which I mentioned before.
But the 12 moves are only 2 different moves in reality, so the whole analysis was for 2 moves, instead of focussing on other moves too.



{
"leelaz": {
"engine-preload-list": [
false,
false,
false,
false,
false,
false,
false,
false,
false
],
"engine-command-list": [
"./katago/katago gtp -model katanetwork.gz -config katago-gtp10.cfg",
"",
"",
"",
"",
"",
"",
"",
""
],
"max-analyze-time-minutes": 99999,
"analyze-update-interval-centisec": 10,
"network-file": "lznetwork.gz",
"_comment": "note, network-file is obselete in Lizzie 0.7+, ignore network-file, kept for compatibility",
"max-game-thinking-time-seconds": 2,
"engine-start-location": ".",
"avoid-keep-variations": 30,
"engine-command": "./leelazero/leelaz --gtp --lagbuffer 0 --weights lznetwork.gz --gpu 0 --gpu 1",
"print-comms": false,
"show-lcb-winrate": false
},
"ui": {
"comment-font-size": 0,
"hold-bestmoves-to-sgf": true,
"shadow-size": 100,
"show-winrate": true,
"autosave-interval-seconds": -1,
"limit-best-move-num": 0,
"stone-indicator-type": 1,
"win-rate-always-black": false,
"board-width": 19,
"show-border": false,
"show-move-number": false,
"winrate-stroke-width": 3,
"show-next-moves": true,
"comment-node-color": [
0,
0,
255
],
"show-comment": true,
"show-leelaz-variation": true,
"show-bestmoves-by-hold": true,
"min-playout-ratio-for-stats": 0.1,
"fancy-stones": true,
"resume-previous-game": false,
"comment-font-color": [
255,
255,
255
],
"show-coordinates": false,
"shadows-enabled": true,
"show-katago-estimate-onsubboard": false,
"show-variation-graph": true,
"show-dynamic-komi": true,
"gtp-console-style": "body {background:#000000; color:#d0d0d0; font-family:Consolas, Menlo, Monaco, 'Ubuntu Mono', monospace; margin:4px;} .command {color:#ffffff;font-weight:bold;} .winrate {color:#ffffff;font-weight:bold;} .coord {color:#ffffff;font-weight:bold;}",
"katago-scoremean-alwaysblack": false,
"katago-notshow-winrate": false,
"minimum-blunder-bar-width": 3,
"large-winrate": false,
"confirm-exit": false,
"show-katago-estimate-onmainboard": true,
"scoremean-line-color": [
255,
0,
255
],
"show-katago-estimate": true,
"show-best-moves": true,
"board-color": [
217,
152,
77
],
"append-winrate-to-comment": false,
"fancy-board": true,
"color-by-winrate-instead-of-visits": false,
"show-captured": true,
"replay-branch-interval-seconds": 1,
"panel-ui": false,
"blunder-bar-color": [
255,
0,
0,
150
],
"weighted-blunder-bar-height": false,
"katago-estimate-mode": "small+dead",
"theme": "Default",
"show-winrate-in-suggestion": true,
"show-scoremean-in-suggestion": true,
"new-move-number-in-branch": true,
"winrate-line-color": [
0,
255,
0
],
"blunder-node-colors": [],
"minPlayoutRatioForStats": 0.1,
"show-katago-boardscoremean": false,
"show-playouts-in-suggestion": true,
"limit-branch-length": 0,
"blunder-winrate-thresholds": [],
"board-position-proportion": 4,
"show-blunder-bar": false,
"only-last-move-number": 0,
"board-height": 19,
"winrate-miss-line-color": [
0,
0,
178
],
"show-status": true,
"handicap-instead-of-winrate": false,
"large-subboard": false,
"comment-background-color": [
0,
0,
0,
200
],
"dynamic-winrate-graph-width": false,
"show-subboard": true,
"show-katago-scoremean": true,
"show-comment-node-color": false,
"board-size": 19
}
}

When network evals hit the cache, they are still a visit in the counted total although the GPU isn't used. Early in the game there are lots of cache hits because of transpositions and multiple lines that lead to the same board states. If you try loading in an SGF mid to late game and start analysis, you should see more 'realistic' performance numbers. There's also a benchmark command you can use, which I believe uses some built in test positions. Speed stats starting from an empty board isn't too useful.

For max performance try using higher --threads and --batchsize than the defaults. Also once you've decided what threads/batchsize to use, run those settings with --full-tuner once.