mirrors/llama.vscode
2
0
Fork 0
mirror of https://github.com/ggml-org/llama.vscode.git synced 2026-05-07 01:15:23 +00:00
Code Issues Projects Releases Packages Wiki Activity
Page: Parallel completions
Pages
Agent commands Chat with AI about llama vscode Chat with AI Code completion Copilot chat model provider Custom eval tool Custom tool Delete models Edit agent Edit with AI Env Generate commit message Health check Home How to use Llama agent Local ai runner Manage agents Manage chat models Manage chats Manage completion models Manage embeddings models Manage envs Manage tools models Mcp support Menu Model selection More context files Parallel completions Rules Skills Statusbar Subagents Update todos tool Use cases
3 Parallel completions
igardev edited this page 2026-01-05 22:22:04 +02:00
Table of Contents

Parallel Completions

Overview

Llama-vscode generates parallel code completions (default 3) if a version of llama.cpp after December, 6, 2025 (commit c42712b) is used. The next completion is shown by pressing Ctrl+], previous completion is shown by pressing Ctrl+[.
The setting max_parallel_completions determines how many completions are generated.

How to use it

  1. Run the completion model and start coding
  2. When a code completion is shown, press Ctrl+] to show the next completion, Ctrl+[ to show the previous completion
  3. Alternatively - you could hover over the shown completion and when the toolbar is shown click the arrows to show the other completions.

Settings:

  • max_parallel_completions: The max number of parallel completions to generate. Default is 3.

Screencast from 2026-01-05 15-05-00.webm