Remove the --torch-compile option (it doesn't do anything currently)

modules/loaders.py

@@ -39,7 +39,6 @@ loaders_and_params = OrderedDict({
         'quant_type',
         'load_in_8bit',
         'load_in_4bit',
-        'torch_compile',
         'attn_implementation',
         'cpu',
         'disk',

modules/shared.py

@@ -62,7 +62,6 @@ group.add_argument('--trust-remote-code', action='store_true', help='Set trust_r
 group.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
 group.add_argument('--no_use_fast', action='store_true', help='Set use_fast=False while loading the tokenizer (it\'s True by default). Use this if you have any problems related to use_fast.')
 group.add_argument('--attn-implementation', type=str, default='sdpa', metavar="IMPLEMENTATION", help='Attention implementation. Valid options: sdpa, eager, flash_attention_2.')
-group.add_argument('--torch-compile', action='store_true', help='Compile the model with torch.compile for improved performance.')
 
 # bitsandbytes 4-bit
 group = parser.add_argument_group('bitsandbytes 4-bit')

modules/transformers_loader.py

@@ -258,9 +258,6 @@ def load_model_HF(model_name):
         print()
         model = LoaderClass.from_pretrained(path_to_model, **params)
 
-    if shared.args.torch_compile:
-        model = torch.compile(model)
-
     return model
 
 

modules/ui.py

@@ -142,7 +142,6 @@ def list_model_elements():
         'num_experts_per_token',
         'load_in_8bit',
         'load_in_4bit',
-        'torch_compile',
         'flash_attn',
         'attn_implementation',
         'cpu',

modules/ui_model_menu.py

@@ -52,7 +52,6 @@ def create_ui():
                             shared.gradio['streaming_llm'] = gr.Checkbox(label="streaming-llm", value=shared.args.streaming_llm, info='Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
                             shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
                             shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)
-                            shared.gradio['torch_compile'] = gr.Checkbox(label="torch-compile", value=shared.args.torch_compile, info='Compile the model with torch.compile for improved performance.')
                             shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant, info='Used by load-in-4bit.')
                             shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
                             shared.gradio['enable_tp'] = gr.Checkbox(label="enable_tp", value=shared.args.enable_tp, info='Enable Tensor Parallelism (TP).')
@@ -131,7 +130,7 @@ def create_ui():
 def create_event_handlers():
     mu = shared.args.multi_user
     if mu:
-        return  
+        return
 
     shared.gradio['loader'].change(loaders.make_loader_params_visible, gradio('loader'), gradio(loaders.get_all_params()), show_progress=False)