llama-cpp 0.4.1

LLM inference in C/C++

Dependencies

cpp-httplib

default features: disabled

Used By

Features

download - Support downloading a model from an URL

Dependencies

cpp-httplib

features: [openssl]

default features: disabled

server - Build llama-server and llama-cli

Dependencies

llama-cpp

features: [tools]

tools - Build tools

Dependencies

miniaudio

stb

Available Versions

0.4.1#0
9030#0
7146#0
6550#0
6301#1
6301#0
5975#0
4743#1
4743#0

Port Content

cmake-config.diff
pkgconfig.diff
portfile.cmake
unvendor.diff
vcpkg.json

This package supports the following triplets:

Supported on all triplets

In classic mode, run the following vcpkg command:

 vcpkg install llama-cpp

In manifest mode, run the following vcpkg command in your project directory:

 vcpkg add port llama-cpp

llama-cpp 0.4.1

Dependencies

Used By

Features

Available Versions

Port Content

Metadata

Supports

Documentation

Homepage

Install