|
63 | 63 | extra_images_max = 4 |
64 | 64 |
|
65 | 65 | # global vars |
66 | | -KcppVersion = "1.97.4" |
| 66 | +KcppVersion = "1.98" |
67 | 67 | showdebug = True |
68 | 68 | kcpp_instance = None #global running instance |
69 | 69 | global_memory = {"tunnel_url": "", "restart_target":"", "input_to_exit":False, "load_complete":False, "restart_override_config_target":""} |
@@ -2615,6 +2615,7 @@ def transform_genparams(genparams, api_format): |
2615 | 2615 | user_message_end = adapter_obj.get("user_end", "") |
2616 | 2616 | assistant_message_start = adapter_obj.get("assistant_start", "\n### Response:\n") |
2617 | 2617 | assistant_message_end = adapter_obj.get("assistant_end", "") |
| 2618 | + assistant_message_gen = adapter_obj.get("assistant_gen", assistant_message_start) |
2618 | 2619 | if isinstance(prompt, str): #needed because comfy SD uses same field name |
2619 | 2620 | if assistant_message_gen and assistant_message_gen!=assistant_message_start: #replace final output tag with unspaced (gen) version if exists |
2620 | 2621 | if prompt.rstrip().endswith("{{[OUTPUT]}}"): |
@@ -7470,7 +7471,7 @@ def range_checker(arg: str): |
7470 | 7471 | compatgroup.add_argument("--usecpu", help="Do not use any GPU acceleration (CPU Only)", action='store_true') |
7471 | 7472 | parser.add_argument("--contextsize", help="Controls the memory allocated for maximum context size, only change if you need more RAM for big contexts. (default 8192).",metavar=('[256 to 262144]'), type=check_range(int,256,262144), default=8192) |
7472 | 7473 | parser.add_argument("--gpulayers", help="Set number of layers to offload to GPU when using GPU. Requires GPU. Set to -1 to try autodetect, set to 0 to disable GPU offload.",metavar=('[GPU layers]'), nargs='?', const=1, type=int, default=-1) |
7473 | | - parser.add_argument("--tensor_split", help="For CUDA and Vulkan only, ratio to split tensors across multiple GPUs, space-separated list of proportions, e.g. 7 3", metavar=('[Ratios]'), type=float, nargs='+') |
| 7474 | + parser.add_argument("--tensor_split", "--tensorsplit", help="For CUDA and Vulkan only, ratio to split tensors across multiple GPUs, space-separated list of proportions, e.g. 7 3", metavar=('[Ratios]'), type=float, nargs='+') |
7474 | 7475 |
|
7475 | 7476 | #more advanced params |
7476 | 7477 | advparser = parser.add_argument_group('Advanced Commands') |
|
0 commit comments