mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2024-11-25 17:29:22 +01:00
Recommend mul_mat_q for llama.cpp
This commit is contained in:
parent
a069f3904c
commit
37e2980e05
@ -111,7 +111,7 @@ def create_ui():
|
|||||||
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
|
shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap)
|
||||||
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
|
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
|
||||||
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
|
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
|
||||||
shared.gradio['mul_mat_q'] = gr.Checkbox(label="mul_mat_q", value=shared.args.mul_mat_q)
|
shared.gradio['mul_mat_q'] = gr.Checkbox(label="mul_mat_q", value=shared.args.mul_mat_q, info='Recommended in most cases. Improves generation speed by 10-20%.')
|
||||||
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.')
|
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.')
|
||||||
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17')
|
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17')
|
||||||
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
|
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
|
||||||
|
Loading…
Reference in New Issue
Block a user