Use AutoGPTQ by default for GPTQ models

README.md

@@ -244,10 +244,18 @@ Optionally, you can use the following command-line flags:
 | `--n_ctx N_CTX` | Size of the prompt context. |
 | `--llama_cpp_seed SEED` | Seed for llama-cpp models. Default 0 (random). |
 
-#### GPTQ
+#### AutoGPTQ
+
+| Flag             | Description |
+|------------------|-------------|
+| `--triton`       | Use triton. |
+| `--desc_act`     | For models that don't have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig. |
+
+#### GPTQ-for-LLaMa
 
 | Flag                      | Description |
 |---------------------------|-------------|
+| `--gptq-for-llama` | Use GPTQ-for-LLaMa to load the GPTQ model instead of AutoGPTQ. |
 | `--wbits WBITS`           | Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
 | `--model_type MODEL_TYPE` | Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
 | `--groupsize GROUPSIZE`   | Group size. |
@@ -258,14 +266,6 @@ Optionally, you can use the following command-line flags:
 | `--warmup_autotune`    | (triton) Enable warmup autotune. |
 | `--fused_mlp`          | (triton) Enable fused mlp. |
 
-#### AutoGPTQ
-
-| Flag             | Description |
-|------------------|-------------|
-| `--autogptq`     | Use AutoGPTQ for loading quantized models instead of the internal GPTQ loader. |
-| `--triton`       | Use triton. |
-|` --desc_act`     | For models that don't have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig. |
-
 #### FlexGen
 
 | Flag             | Description |

modules/models.py

@@ -81,10 +81,10 @@ def load_model(model_name):
         logger.error('The path to the model does not exist. Exiting.')
         return None, None
 
-    if shared.args.autogptq:
-        load_func = AutoGPTQ_loader
-    elif shared.args.wbits > 0:
+    if shared.args.gptq_for_llama:
         load_func = GPTQ_loader
+    elif Path(f'{shared.args.model_dir}/{model_name}/quantize_config.json').exists() or shared.args.wbits > 0:
+        load_func = AutoGPTQ_loader
     elif shared.model_type == 'llamacpp':
         load_func = llamacpp_loader
     elif shared.model_type == 'rwkv':

modules/shared.py

@@ -141,7 +141,8 @@ parser.add_argument('--warmup_autotune', action='store_true', help='(triton) Ena
 parser.add_argument('--fused_mlp', action='store_true', help='(triton) Enable fused mlp.')
 
 # AutoGPTQ
-parser.add_argument('--autogptq', action='store_true', help='Use AutoGPTQ for loading quantized models instead of the internal GPTQ loader.')
+parser.add_argument('--gptq-for-llama', action='store_true', help='Use GPTQ-for-LLaMa to load the GPTQ model instead of AutoGPTQ.')
+parser.add_argument('--autogptq', action='store_true', help='DEPRECATED')
 parser.add_argument('--triton', action='store_true', help='Use triton.')
 parser.add_argument('--desc_act', action='store_true', help='For models that don\'t have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
 
@@ -181,12 +182,9 @@ parser.add_argument('--multimodal-pipeline', type=str, default=None, help='The m
 args = parser.parse_args()
 args_defaults = parser.parse_args([])
 
-# Deprecation warnings for parameters that have been renamed
-deprecated_dict = {}
-for k in deprecated_dict:
-    if getattr(args, k) != deprecated_dict[k][1]:
-        logger.warning(f"--{k} is deprecated and will be removed. Use --{deprecated_dict[k][0]} instead.")
-        setattr(args, deprecated_dict[k][0], getattr(args, k))
+# Deprecation warnings
+if args.autogptq:
+    logger.warning('--autogptq has been deprecated and will be removed soon. AutoGPTQ is now used by default for GPTQ models.')
 
 # Security warnings
 if args.trust_remote_code:

modules/ui.py

@@ -30,7 +30,7 @@ theme = gr.themes.Default(
 
 
 def list_model_elements():
-    elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'trust_remote_code', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'autogptq', 'triton', 'desc_act', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
+    elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'trust_remote_code', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'gptq_for_llama', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'triton', 'desc_act', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
     for i in range(torch.cuda.device_count()):
         elements.append(f'gpu_memory_{i}')
 

server.py

@@ -393,12 +393,12 @@ def create_model_menus():
                 with gr.Row():
                     with gr.Column():
                         gr.Markdown('AutoGPTQ')
-                        shared.gradio['autogptq'] = gr.Checkbox(label="autogptq", value=shared.args.autogptq, info='Activate AutoGPTQ loader. gpu-memory should be used for CPU offloading instead of pre_layer.')
                         shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
                         shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.')
 
                     with gr.Column():
                         gr.Markdown('GPTQ-for-LLaMa')
+                        shared.gradio['gptq_for_llama'] = gr.Checkbox(label="gptq-for-llama", value=shared.args.gptq_for_llama, info='Use GPTQ-for-LLaMa to load the GPTQ model instead of AutoGPTQ. pre_layer should be used for CPU offloading instead of gpu-memory.')
                         with gr.Row():
                             shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
                             shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")