a simple web interface to chat with a model in rkllm
Find a file
2025-02-04 13:16:32 +01:00
include Started on the CL version 2025-02-04 06:27:11 +01:00
lib Started on the CL version 2025-02-04 06:27:11 +01:00
static remove ningle and create simple router 2025-02-04 13:16:32 +01:00
.gitignore Started on the CL version 2025-02-04 06:27:11 +01:00
fix_freq_rk3576.sh initial commit 2025-02-01 21:27:56 +01:00
fix_freq_rk3588.sh initial commit 2025-02-01 21:27:56 +01:00
flask_server.py Started on the CL version 2025-02-04 06:27:11 +01:00
README.md initial commit 2025-02-01 21:27:56 +01:00
requirements.txt initial commit 2025-02-01 21:27:56 +01:00
rkllm-server.asd remove ningle and create simple router 2025-02-04 13:16:32 +01:00
rkllm.py initial commit 2025-02-01 21:27:56 +01:00
server.lisp remove ningle and create simple router 2025-02-04 13:16:32 +01:00
start_server.sh initial commit 2025-02-01 21:27:56 +01:00

rkllm server

Hosts a simple flask-based chat interface to a rkllm-model at localhost:8080.

Install

On a r3588 system:

git clone "<repo>/rkllm_server"
cd rkllm_server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
deactivate

you can now start the server with:

bash ./start_server.sh "/path/to/model.rkllm"

The first time on each boot it will ask for a sudo password to fix the npu speed (see [fix_freq_rk3588.sh]).