FlorSanders

Setup Guide for llama.cpp on Nvidia Jetson Nano 2GB

This is a full account of the steps I ran to get llama.cpp running on the Nvidia Jetson Nano 2GB. It accumulates multiple different fixes and tutorials, whose contributions are referenced at the bottom of this README.

Procedure

At a high level, the procedure to install llama.cpp on a Jetson Nano consists of 3 steps.

1. Compile the gcc 8.5 compiler from source.

kyo-takano

import gzip

def gzip_search(query: str, candidate_chunks: list[str], top_k: int=1):
    """
    文字列ベースで類似したテキストチャンクを推定するアルゴリズム.
    `query`, `chunk`, および`query + " " + chunk`をそれぞれgzipで圧縮し、編集距離のようなものをベースに評価する.

    Parameters:
        query (str): 検索クエリとして使用する文字列.
        top_k (int, optional): 返される類似チャンクの上位k個を指定する (default: 1).

ejkarne

defaults write com.apple.WindowManager GloballyEnabled -bool [True/False] Adjusts whether Stage Manager is enabled or not.

defaults write com.apple.WindowManager AutoHide -bool [True/False] Adjusts auto hide behavior. This option controls the "Show Recent Apps" and "Hide Recent Apps" GUI option.

defaults write com.apple.WindowManager AutoHideOverlapThreshold -int [-2147483647...2147483647] Unsure what this option does. Should be noted that when AutoHide is set to False and this option is set to -17 or lower Stage Manager behaves as if AutoHide is set to True.

defaults write com.apple.WindowManager LeftStripMaximumRowCount -int [-2147483647...2147483647]

netsensei

Creating and managing an SSH session in the background

Sources:
https://stackoverflow.com/questions/2241063/bash-script-to-set-up-a-temporary-ssh-tunnel/15198031#15198031
https://lists.gt.net/openssh/dev/48040#48040

Starting an SSH session

$ ssh -M -S my-ctrl-socket -fnNT user@host.tld