local-llm-pilot-completion

Inline completion with codeqwen1.5.

Setup

llm server

Two ways to run codeqwen1.5 at local pc:

1. ollama

ollama pull codeqwen:v1.5-code

ollama serve

2. lmdeploy

lmdeploy serve api_server Qwen/CodeQwen1.5-7B

Test ollama/lmdeploy api url.

vscode settings

set ollama/openai api url.

Requirements

• running ollama or lmdeploy server with codeqwen1.5

Release Notes

0.0.1

Initial release of local llm pilot completion

0.0.2

Support openai api type

0.0.4

Support single line and trim