@@ -73,6 +73,7 @@ def __init__(self):
7373 self .aic_backend_version = None
7474 self .num_gpus_per_node = 8
7575 self .deploy_after_profile = False
76+ self .pick_with_webui = False
7677 # Provide minimal model_info to avoid HF queries
7778 self .model_info = ModelInfo (
7879 model_size = 16384.0 ,
@@ -116,6 +117,7 @@ def __init__(self):
116117 self .aic_backend_version = None
117118 self .num_gpus_per_node = 8
118119 self .deploy_after_profile = False
120+ self .pick_with_webui = False
119121 self .model_info = ModelInfo (
120122 model_size = 16384.0 ,
121123 architecture = "TestArchitecture" ,
@@ -180,6 +182,7 @@ def __init__(self):
180182 self .aic_backend_version = None
181183 self .num_gpus_per_node = 8
182184 self .deploy_after_profile = False
185+ self .pick_with_webui = False
183186 self .model_info = ModelInfo (
184187 model_size = 16384.0 ,
185188 architecture = "TestArchitecture" ,
@@ -233,6 +236,7 @@ def __init__(self):
233236 self .aic_backend_version = None
234237 self .num_gpus_per_node = 8
235238 self .deploy_after_profile = False
239+ self .pick_with_webui = False
236240 self .model_info = ModelInfo (
237241 model_size = 65536.0 ,
238242 architecture = "TestMoEArchitecture" ,
@@ -309,6 +313,7 @@ def __init__(self):
309313 # Set to 0 to trigger auto-generation path
310314 self .num_gpus_per_node = 0
311315 self .deploy_after_profile = False
316+ self .pick_with_webui = False
312317 self .enable_gpu_discovery = True
313318
314319 return Args ()
@@ -376,6 +381,7 @@ def __init__(self):
376381 self .aic_backend_version = None
377382 self .num_gpus_per_node = 0
378383 self .deploy_after_profile = False
384+ self .pick_with_webui = False
379385 self .enable_gpu_discovery = True
380386
381387 return Args ()
@@ -443,6 +449,7 @@ def __init__(self):
443449 self .aic_backend_version = None
444450 self .num_gpus_per_node = 0
445451 self .deploy_after_profile = False
452+ self .pick_with_webui = False
446453 self .enable_gpu_discovery = True
447454
448455 return Args ()
0 commit comments