9 lines
219 B
Markdown
9 lines
219 B
Markdown
|
# dumbpilot
|
||
|
|
|
||
|
|
Get inline completions using llama.cpp as as server backend
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
1. start llama.cpp/server in the background or on a remote machine
|
||
|
|
2. configure the host
|
||
|
|
3. press `ctrl+shift+l` to use code prediction
|