oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-07 07:33:47 +00:00
Code Issues Projects Releases Packages Wiki Activity

llama.cpp: allow ctx_size=0 for auto context via --fit

Browse source
This commit is contained in:
oobabooga 2026-03-04 19:33:20 -08:00
parent fbfcd59fe0
commit 69fa4dd0b1
6 changed files with 13 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/models_settings.py
View file

@ -418,7 +418,7 @@ def update_gpu_layers_and_vram(loader, model, gpu_layers, ctx_size, cache_type):
Compute the estimated VRAM usage for the given GPU layers and return
an HTML string for the UI display.
"""
if loader != 'llama.cpp' or model in ["None", None] or not model.endswith(".gguf") or gpu_layers < 0:
if loader != 'llama.cpp' or model in ["None", None] or not model.endswith(".gguf") or gpu_layers < 0 or ctx_size == 0:
return "<div id=\"vram-info\"'>Estimated VRAM to load the model:</div>"
vram_usage = estimate_vram(model, gpu_layers, ctx_size, cache_type)