feat: get VRAM state - Githubissues

Description of change

feat: get VRAM state
feat: chatWrapper getter on a LlamaChatSession
fix(resolveChatWrapperBasedOnModel): use llamaChat wrapper for llama models only if there's a chat sub-variant
fix: update latest build on postinstall compilation

How to get the current VRAM state

import {getLlama} from "node-llama-cpp";

const llama = await getLlama();
const vramState = llama.getVramState();

console.log("Total VRAM:", vramState.total);
console.log("Used VRAM:", vramState.used);
console.log("Free VRAM:", vramState.free);

Pull-Request Checklist

[x] Code is up-to-date with the master branch
[x] npm run format to apply eslint formatting
[x] npm run test passes with this change
[x] This pull request links relevant issues as Fixes #0000
[ ] There are new or updated unit tests validating the change
[ ] Documentation has been updated to reflect this change
[x] The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)

withcatai / node-llama-cpp

feat: get VRAM state #161

Description of change

How to get the current VRAM state

Pull-Request Checklist