༺ Initial H ༻ alsyundawy

Install dependencies:

brew install libomp vulkan-headers glslang molten-vk shaderc vulkan-loader

Now Molten-VK is already above v1.4 -> therefore no need to get older version and manually apply PR2434.

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build -DLLAMA_CURL=1 -DGGML_METAL=OFF -DGGML_VULKAN=ON

I found a way to run llama.cpp with GPU support on my 2019 Intel MacBook Pro, with the help of Vulkan.

Thanks to ollama/ollama#1016 (comment) an following comments which helped me find the right build flags.

First download MoltenVK-macos.tar (I used v1.3.0-rc1 at the time) from https://github.com/KhronosGroup/MoltenVK/releases

Not sure all these packages are required, but I ran brew install libomp vulkan-headers glslang molten-vk shaderc vulkan-loader. You probably also need to install cmake and potentially other tools I already had installed on my system.

Then clone and build llama.cpp (replace /path/to/MoltenVK_macos with the actual path you have MoltenVK_macos):

Swappiness controls the tendancy the kernel wishes to swap.

Even with free memory the kernel may swap.

100 means aggressively swap 0 means wait until the last minute to swap

To check current swappiness cat /proc/sys/vm/swappiness

Never touch your local /etc/hosts file in OS X again

To setup your computer to work with *.test domains, e.g. project.test, awesome.test and so on, without having to add to your hosts file each time.

Requirements

Homebrew
Mountain Lion -> High Sierra

	#!/usr/bin/env bash
	# VMware Fusion Latest Version Downloader, Installer, and Updater
	# This script automatically finds, downloads, and optionally installs the highest version available
	#
	# Inspired by: https://gist.github.com/jetfir3/6b28fd279bbcadbae70980bd711a844f
	#
	# Usage: $0 [-y] [-i] [-d] [-f] [-t <dmg_path>]
	# -y: Skip download confirmation prompt
	# -i: Automatically install after download (implies -y)
	# -d: Download only (skip installation even if -i is specified)

	#!/bin/bash
	set -o errexit

	clear
	printf "\n* This script will download a cloud image and create a Proxmox VM template from it. *\n\n"

	### HOW TO USE
	### Pre-req:
	### - run on a Proxmox 6 server
	### - a dhcp server should be active on vmbr1

	#!/bin/bash
	set -o errexit

	clear
	printf "\n* This script will download a cloud image and create a Proxmox VM template from it. *\n\n"

	### HOW TO USE
	### Pre-req:
	### - run on a Proxmox 6 server
	### - a dhcp server should be active on vmbr1

	#!/bin/bash

	# Script designed to upgrade PNETLab from almost any version to NEW_PNETLAB_VERSION version
	# Requirement: Not having PNETLab 6.x installed for being able to upgrade to NEW_PNETLAB_VERSION
	# This script avoids to make this upgrade process twice

	# CONSTANTS
	NEW_PNETLAB_VERSION=5.3.11
	GREEN='\033[32m'
	NO_COLOR='\033[0m'

	#!/bin/bash

	echo "Please run as root"
	echo ""

	wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=13TU6pnsx1dX5tHOQjgVh2URM9AMqeKcD' -O- \| sed -rn 's/.confirm=([0-9A-Za-z_]+)./\1\n/p')&id=13TU6pnsx1dX5tHOQjgVh2URM9AMqeKcD" -O gcc48-c++-4.8.5-1.el6.x86_64.rpm && rm -rf /tmp/cookies.txt
	rpm -i gcc48-c++-4.8.5-1.el6.x86_64.rpm

	mv /usr/bin/gcc48 /usr/bin/gcc && mv /usr/bin/g++48 /usr/bin/g++

	#!/bin/sh

	# Update glibc ke 2.17 untuk CentOS 6

	# Unduh paket glibc
	wget -c \
	http://copr-be.cloud.fedoraproject.org/results/mosquito/myrepo-el6/epel-6-x86_64/glibc-2.17-55.fc20/glibc-2.17-55.el6.x86_64.rpm \
	http://copr-be.cloud.fedoraproject.org/results/mosquito/myrepo-el6/epel-6-x86_64/glibc-2.17-55.fc20/glibc-common-2.17-55.el6.x86_64.rpm \
	http://copr-be.cloud.fedoraproject.org/results/mosquito/myrepo-el6/epel-6-x86_64/glibc-2.17-55.fc20/glibc-devel-2.17-55.el6.x86_64.rpm \
	http://copr-be.cloud.fedoraproject.org/results/mosquito/myrepo-el6/epel-6-x86_64/glibc-2.17-55.fc20/glibc-headers-2.17-55.el6.x86_64.rpm