simcop2387/text-generation-webui-mirror
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-06-07 14:17:09 -04:00
Code Issues Projects Releases Packages Wiki Activity

Only compute VRAM/GPU layers for llama.cpp models

Browse source
This commit is contained in:
oobabooga 2025-05-16 10:02:30 -07:00
parent 9ec9b1bf83
commit 253e85a519
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modules/models_settings.py
View file

@ -441,7 +441,7 @@ def update_gpu_layers_and_vram(loader, model, gpu_layers, ctx_size, cache_type,
- If for_ui=True: (vram_info_update, gpu_layers_update) or just vram_info_update - If for_ui=True: (vram_info_update, gpu_layers_update) or just vram_info_update
- If for_ui=False: (vram_usage, adjusted_layers) or just vram_usage - If for_ui=False: (vram_usage, adjusted_layers) or just vram_usage
""" """
if loader != 'llama.cpp' or model in ["None", None]: if loader != 'llama.cpp' or model in ["None", None] or not model.endswith(".gguf"):
vram_info = "<div id=\"vram-info\"'>Estimated VRAM to load the model:</span>" vram_info = "<div id=\"vram-info\"'>Estimated VRAM to load the model:</span>"
if for_ui: if for_ui:
return (vram_info, gr.update()) if auto_adjust else vram_info return (vram_info, gr.update()) if auto_adjust else vram_info