ComfyUI Node
Llama.cpp Python Server
A ComfyUI node in LLM / llama.cpp with 6 inputs and 1 output.
Llama.cpp Python Server
- server_url
◄model_pathmodels/llama/model.gguf►
◄host127.0.0.1►
◄port8000►
◄n_gpu_layers-1►
◄auto_starton►
◄time_out120.00►
CategoryLLM / llama.cpp
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| model_path | STRING | models/llama/model.gguf | — |
| host | STRING | 127.0.0.1 | — |
| port | INT | 80001–65535 | — |
| n_gpu_layers | INT | -1-5–999 | — |
| auto_start | COMBO | on | 2 options: on, off |
| time_out | FLOAT | 120.000–999 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| server_url | STRING | — |