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

Split by rows instead of layers for llama.cpp multi-gpu (#5435)

Browse source
This commit is contained in:
Forkoz 2024-02-05 02:36:40 +00:00 • committed by GitHub
parent 3df7e151f7
commit 2a45620c85
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/ui_model_menu.py
View file

@ -107,6 +107,7 @@ def create_ui():
with gr.Column():
shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.')
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.')
shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split model by rows across GPUs. Improves performance on some cards.')
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
shared.gradio['no_inject_fused_attention'] = gr.Checkbox(label="no_inject_fused_attention", value=shared.args.no_inject_fused_attention, info='Disable fused attention. Fused attention improves inference performance but uses more VRAM. Fuses layers for AutoAWQ. Disable if running low on VRAM.')
shared.gradio['no_inject_fused_mlp'] = gr.Checkbox(label="no_inject_fused_mlp", value=shared.args.no_inject_fused_mlp, info='Affects Triton only. Disable fused MLP. Fused MLP improves performance but uses more VRAM. Disable if running low on VRAM.')