oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 15:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity

Remove ExLlamaV2 backend

Browse source 
- archived upstream: 7dc12af3a8
- replaced by ExLlamaV3, which has much better quantization accuracy
This commit is contained in:
oobabooga 2026-03-05 13:57:21 -08:00
parent 134ac8fc29
commit 2f08dce7b0
19 changed files with 22 additions and 713 deletions
Download patch file Download diff file Expand all files Collapse all files

6
modules/models_settings.py
View file

@ -216,12 +216,8 @@ def infer_loader(model_name, model_settings, hf_quant_method=None):
loader = 'llama.cpp'
elif hf_quant_method == 'exl3':
loader = 'ExLlamav3'
elif hf_quant_method in ['exl2', 'gptq']:
loader = 'ExLlamav2_HF'
elif re.match(r'.*exl3', model_name.lower()):
loader = 'ExLlamav3'
elif re.match(r'.*exl2', model_name.lower()):
loader = 'ExLlamav2_HF'
else:
loader = 'Transformers'
@ -255,7 +251,7 @@ def apply_model_settings_to_state(model, state):
model_settings = get_model_metadata(model)
if 'loader' in model_settings:
loader = model_settings.pop('loader')
if not ((loader == 'ExLlamav2_HF' and state['loader'] == 'ExLlamav2') or (loader == 'ExLlamav3_HF' and state['loader'] == 'ExLlamav3')):
if not (loader == 'ExLlamav3_HF' and state['loader'] == 'ExLlamav3'):
state['loader'] = loader
for k in model_settings: