[AMD] Add prealloc token env for mori-ep (#22329)
This commit is contained in:
@@ -5188,7 +5188,7 @@ class ServerArgs:
|
||||
type=str,
|
||||
choices=["normal", "low_latency", "auto"],
|
||||
default="auto",
|
||||
help="Select the mode when enable DeepEP MoE, could be `normal`, `low_latency` or `auto`. Default is `auto`, which means `low_latency` for decode batch and `normal` for prefill batch.",
|
||||
help="Select the mode when enable DeepEP or MoriEP MoE, could be `normal`, `low_latency` or `auto`. Default is `auto`, which means `low_latency` for decode batch and `normal` for prefill batch.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--ep-num-redundant-experts",
|
||||
|
||||
Reference in New Issue
Block a user