oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-26 10:24:25 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

llama.cpp: Document the --device-draft syntax

Browse source
This commit is contained in:
oobabooga 2025-04-24 09:20:11 -07:00
parent f1b64df8dd
commit 93fd4ad25d
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -134,7 +134,7 @@ group = parser.add_argument_group('Speculative decoding')
group.add_argument('--model-draft', type=str, default=None, help='Path to the draft model for speculative decoding.')
group.add_argument('--draft-max', type=int, default=4, help='Number of tokens to draft for speculative decoding.')
group.add_argument('--gpu-layers-draft', type=int, default=0, help='Number of layers to offload to the GPU for the draft model.')
group.add_argument('--device-draft', type=str, default=None, help='Comma-separated list of devices to use for offloading the draft model.')
group.add_argument('--device-draft', type=str, default=None, help='Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1')
group.add_argument('--ctx-size-draft', type=int, default=0, help='Size of the prompt context for the draft model. If 0, uses the same as the main model.')
# ExLlamaV2

2
modules/ui_model_menu.py
View file

@ -100,7 +100,7 @@ def create_ui():
shared.gradio['draft_max'] = gr.Number(label="draft-max", precision=0, step=1, value=shared.args.draft_max, info='Number of tokens to draft for speculative decoding.')
shared.gradio['gpu_layers_draft'] = gr.Slider(label="gpu-layers-draft", minimum=0, maximum=256, value=shared.args.gpu_layers_draft, info='Number of layers to offload to the GPU for the draft model.')
shared.gradio['device_draft'] = gr.Textbox(label="device-draft", value=shared.args.device_draft, info='Comma-separated list of devices to use for offloading the draft model.')
shared.gradio['device_draft'] = gr.Textbox(label="device-draft", value=shared.args.device_draft, info='Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1')
shared.gradio['ctx_size_draft'] = gr.Number(label="ctx-size-draft", precision=0, step=256, value=shared.args.ctx_size_draft, info='Size of the prompt context for the draft model. If 0, uses the same as the main model.')
with gr.Column():