mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add gpu_split param to ExLlama

Browse source 
Adapted from code created by Ph0rk0z. Thank you Ph0rk0z.
This commit is contained in:
oobabooga 2023-06-16 20:49:36 -03:00
parent cb9be5db1c
commit 5f392122fd
6 changed files with 20 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
server.py
View file

@ -216,7 +216,7 @@ def create_model_menus():
shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")
shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0)
shared.gradio['autogptq_info'] = gr.Markdown('On some systems, AutoGPTQ can be 2x slower than GPTQ-for-LLaMa. You can manually select the GPTQ-for-LLaMa loader above.')
shared.gradio['exllama_info'] = gr.Markdown('ExLlama has to be installed manually. See the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).')
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-slit', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
@ -235,6 +235,7 @@ def create_model_menus():
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.')
shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa is currently 2x faster than AutoGPTQ on some systems. It is installed by default with the one-click installers. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).')
shared.gradio['exllama_info'] = gr.Markdown('ExLlama has to be installed manually. See the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).')
with gr.Column():
with gr.Row():