oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 14:17:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add StreamingLLM for llamacpp & llamacpp_HF (2nd attempt) (#5669)

Browse source
This commit is contained in:
oobabooga 2024-03-09 00:25:33 -03:00 • committed by GitHub
parent 9271e80914
commit afb51bd5d6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 147 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/ui_model_menu.py
View file

@ -117,6 +117,8 @@ def create_ui():
shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.')
shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)
shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.')
shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
shared.gradio['attention_sink_size'] = gr.Number(label="attention_sink_size", value=shared.args.attention_sink_size)
shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu, info='llama.cpp: Use llama-cpp-python compiled without GPU acceleration. Transformers: use PyTorch in CPU mode.')
shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split the model by rows across GPUs. This may improve multi-gpu performance.')
shared.gradio['no_offload_kqv'] = gr.Checkbox(label="no_offload_kqv", value=shared.args.no_offload_kqv, info='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.')