Simplify Router arguments passing and build it in docker image (#9964)
This commit is contained in:
@@ -367,7 +367,6 @@ class ServerArgs:
|
||||
disaggregation_prefill_pp: Optional[int] = 1
|
||||
disaggregation_ib_device: Optional[str] = None
|
||||
num_reserved_decode_tokens: int = 512 # used for decode kv cache offload in PD
|
||||
pdlb_url: Optional[str] = None
|
||||
|
||||
# For model weight update
|
||||
custom_weight_loader: Optional[List[str]] = None
|
||||
@@ -2071,12 +2070,6 @@ class ServerArgs:
|
||||
default=ServerArgs.num_reserved_decode_tokens,
|
||||
help="Number of decode tokens that will have memory reserved when adding new request to the running batch.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--pdlb-url",
|
||||
type=str,
|
||||
default=None,
|
||||
help="The URL of the PD disaggregation load balancer. If set, the prefill/decode server will register with the load balancer.",
|
||||
)
|
||||
|
||||
# Custom weight loader
|
||||
parser.add_argument(
|
||||
|
||||
Reference in New Issue
Block a user