How to add multiple extensions to --extensions?

[yhyu13]

Describe the bug

I know you can enable multiple extensions in the UI webpage, but how do you lunch them at start by using the cmd arg --extensions?

The README.md says

--extensions EXTENSIONS [EXTENSIONS ...]	The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.

But

--extensions llava long-term-memory 

does not seem to work

Is there an existing issue for this?

• I have searched the existing issues

Reproduction

Install extensions

git clone https://github.com/wawawario2/long_term_memory extensions/long_term_memory
pip install -r extensions/long_term_memory/requirements.txt

git clone https://huggingface.co/wojtab/llava-13b-v0-4bit-128g.git ./models
cd ./models/llava-13b-v0-4bit-128g && git lfs pull

Then run with these args

python server.py --model llava-13b-v0-4bit-128g --model_type llama --extensions llava long-term-memory --share

Screenshot

No response

Logs

Notice only llava is loaded but not long-term-memory

Gradio HTTP request redirected to localhost :)
Warning: the gradio "share link" feature downloads a proprietary and
unaudited blob to create a reverse tunnel. This is potentially dangerous.

bin /home/hangyu5/anaconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda113.so
Loading llava-13b-v0-4bit-128g...
Found the following quantized model: models/llava-13b-v0-4bit-128g/llava-13b-v0-4bit-128g.safetensors
Loading model ...
Done.
Using the following device map for the quantized model: {'model.embed_tokens': 0, 'model.layers.0': 0, 'model.layers.1': 0, 'model.layers.2': 0, 'model.layers.3': 0, 'model.layers.4': 0, 'model.layers.5': 0, 'model.layers.6': 0, 'model.layers.7': 0, 'model.layers.8': 0, 'model.layers.9': 0, 'model.layers.10': 0, 'model.layers.11': 0, 'model.layers.12': 0, 'model.layers.13': 0, 'model.layers.14': 0, 'model.layers.15': 0, 'model.layers.16': 0, 'model.layers.17': 0, 'model.layers.18': 1, 'model.layers.19': 1, 'model.layers.20': 1, 'model.layers.21': 1, 'model.layers.22': 1, 'model.layers.23': 1, 'model.layers.24': 1, 'model.layers.25': 1, 'model.layers.26': 1, 'model.layers.27': 1, 'model.layers.28': 1, 'model.layers.29': 1, 'model.layers.30': 1, 'model.layers.31': 1, 'model.layers.32': 1, 'model.layers.33': 1, 'model.layers.34': 1, 'model.layers.35': 1, 'model.layers.36': 1, 'model.layers.37': 1, 'model.layers.38': 1, 'model.layers.39': 1, 'model.norm': 1, 'lm_head': 1}
Loaded the model in 5.02 seconds.
Loading the extension "llava"... Ok.
LLaVA - Loading openai/clip-vit-large-patch14 as torch.float32 on cuda:0...
LLaVA - Loading liuhaotian/LLaVA-13b-pretrain-projector-v0 as torch.float32 on cuda:0...
LLaVA supporting models loaded, took 3.08 seconds
Running on local URL:  http://127.0.0.1:7860
Running on public URL: https://6c4e8aa87007c87f31.gradio.live

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces

### System Info

```shell
Ubuntu 22.04
dual RTX 3090

[IJumpAround]

Extensions are space separated, but long-term-memory should be long_term_memory

[ChrisRhw]

I think only one extension can use the custom_generate_chat_prompt function, and both llava and long_term_memory use them. So right now only the first extension will works.

[yhyu13]

It magically works now