Merge branch 'elwolf6-max_memory'

modules/extensions.py

@@ -7,7 +7,7 @@ available_extensions = []
 
 def load_extensions():
     global extension_state
-    for i,ext in enumerate(shared.args.extensions.split(',')):
+    for i,ext in enumerate(shared.args.extensions):
         if ext in available_extensions:
             print(f'Loading the extension "{ext}"... ', end='')
             ext_string = f"extensions.{ext}.script"

modules/models.py

@@ -96,7 +96,12 @@ def load_model(model_name):
             params.append("load_in_8bit=True" if shared.args.load_in_8bit else "torch_dtype=torch.bfloat16" if shared.args.bf16 else "torch_dtype=torch.float16")
 
             if shared.args.gpu_memory:
-                params.append(f"max_memory={{0: '{shared.args.gpu_memory or '99'}GiB', 'cpu': '{shared.args.cpu_memory or '99'}GiB'}}")
+                memory_map = shared.args.gpu_memory
+                max_memory = f"max_memory={{0: '{memory_map[0]}GiB'"
+                for i in range(1, len(memory_map)):
+                    max_memory += (f", {i}: '{memory_map[i]}GiB'")
+                max_memory += (f", 'cpu': '{shared.args.cpu_memory or '99'}GiB'}}")
+                params.append(max_memory)
             elif not shared.args.load_in_8bit:
                 total_mem = (torch.cuda.get_device_properties(0).total_memory/(1024*1024))
                 suggestion = round((total_mem-1000)/1000)*1000

modules/shared.py

@@ -44,17 +44,17 @@ parser.add_argument('--bf16', action='store_true', help='Load the model with bfl
 parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.')
 parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')
 parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".')
-parser.add_argument('--gpu-memory', type=int, help='Maximum GPU memory in GiB to allocate. This is useful if you get out of memory errors while trying to generate text. Must be an integer number.')
+parser.add_argument('--gpu-memory', type=int, nargs="+", help='Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs.')
 parser.add_argument('--cpu-memory', type=int, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.')
 parser.add_argument('--flexgen', action='store_true', help='Enable the use of FlexGen offloading.')
-parser.add_argument('--percent', nargs="+", type=int, default=[0, 100, 100, 0, 100, 0], help='FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).')
+parser.add_argument('--percent', type=int, nargs="+", default=[0, 100, 100, 0, 100, 0], help='FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0).')
 parser.add_argument("--compress-weight", action="store_true", help="FlexGen: activate weight compression.")
 parser.add_argument('--deepspeed', action='store_true', help='Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.')
 parser.add_argument('--nvme-offload-dir', type=str, help='DeepSpeed: Directory to use for ZeRO-3 NVME offloading.')
 parser.add_argument('--local_rank', type=int, default=0, help='DeepSpeed: Optional argument for distributed setups.')
 parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time. This improves the text generation performance.')
 parser.add_argument('--settings', type=str, help='Load the default interface settings from this json file. See settings-template.json for an example.')
-parser.add_argument('--extensions', type=str, help='The list of extensions to load. If you want to load more than one extension, write the names separated by commas and between quotation marks, "like,this".')
+parser.add_argument('--extensions', type=str, nargs="+", help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.')
 parser.add_argument('--listen', action='store_true', help='Make the web UI reachable from your local network.')
 parser.add_argument('--listen-port', type=int, help='The listening port that the server will use.')
 parser.add_argument('--share', action='store_true', help='Create a public URL. This is useful for running the web UI on Google Colab or similar.')