oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 22:27:29 +00:00
Code Issues Projects Releases Packages Wiki Activity

Remove AutoAWQ as a standalone loader

Browse source 
(it works better through transformers)
This commit is contained in:
oobabooga 2024-07-23 15:26:02 -07:00
parent f66ab63d64
commit e6181e834a
7 changed files with 2 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

9
modules/shared.py
View file

@ -89,7 +89,7 @@ group.add_argument('--idle-timeout', type=int, default=0, help='Unload model aft
# Model loader
group = parser.add_argument_group('Model loader')
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ.')
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ.')
# Transformers/Accelerate
group = parser.add_argument_group('Transformers/Accelerate')
@ -160,10 +160,6 @@ group.add_argument('--disable_exllamav2', action='store_true', help='Disable ExL
group.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
group.add_argument('--groupsize', type=int, default=-1, help='Group size.')
# AutoAWQ
group = parser.add_argument_group('AutoAWQ')
group.add_argument('--no_inject_fused_attention', action='store_true', help='Disable the use of fused attention, which will use less VRAM at the cost of slower inference.')
# HQQ
group = parser.add_argument_group('HQQ')
group.add_argument('--hqq-backend', type=str, default='PYTORCH_COMPILE', help='Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.')
@ -217,6 +213,7 @@ group.add_argument('--model_type', type=str, help='DEPRECATED')
group.add_argument('--pre_layer', type=int, nargs='+', help='DEPRECATED')
group.add_argument('--checkpoint', type=str, help='DEPRECATED')
group.add_argument('--monkey-patch', action='store_true', help='DEPRECATED')
group.add_argument('--no_inject_fused_attention', action='store_true', help='DEPRECATED')
args = parser.parse_args()
args_defaults = parser.parse_args([])
@ -267,8 +264,6 @@ def fix_loader_name(name):
return 'ExLlamav2'
elif name in ['exllamav2-hf', 'exllamav2_hf', 'exllama-v2-hf', 'exllama_v2_hf', 'exllama-v2_hf', 'exllama2-hf', 'exllama2_hf', 'exllama-2-hf', 'exllama_2_hf', 'exllama-2_hf']:
return 'ExLlamav2_HF'
elif name in ['autoawq', 'awq', 'auto-awq']:
return 'AutoAWQ'
elif name in ['hqq']:
return 'HQQ'
elif name in ['tensorrt', 'tensorrtllm', 'tensorrt_llm', 'tensorrt-llm', 'tensort', 'tensortllm']: