寂听 jitingcn

Please use this page for SlimeVR setup instructions and downloads:

https://docs.slimevr.dev/server-setup/slimevr-setup.html

For years, people have been using jemalloc with ruby. There were various benchmarks and discussions. Legend had it that Jemalloc 5 didn't work as well as Jemalloc 3.

Then, one day, hope appeared on the horizon. @wjordan offered a config for Jemalloc 5.

Ubuntu/Debian

FROM ruby:3.1.2-bullseye
RUN apt-get update ; \

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

	#Requires -RunAsAdministrator
	# Fix for https://github.com/microsoft/WSL/issues/4177

	$MethodDefinition = @'
	[DllImport("ws2_32.dll", CharSet = CharSet.Unicode)]
	public static extern int WSCSetApplicationCategory([MarshalAs(UnmanagedType.LPWStr)] string Path, uint PathLength, [MarshalAs(UnmanagedType.LPWStr)] string Extra, uint ExtraLength, uint PermittedLspCategories, out uint pPrevPermLspCat, out int lpErrno);
	'@

	$Ws2Spi = Add-Type -MemberDefinition $MethodDefinition -Name 'Ws2Spi' -PassThru

	// ==UserScript==
	// @name m3u8Download
	// @namespace https://github.com/bambooGHT
	// @version 1.2.8
	// @description 修复bug
	// @author bambooGHT
	// @match https://canan8181.com/*
	// @match https://rnqq.jp/*
	// @match https://kemomimirefle.net/*
	// @match https://nicochannel.jp/*