[PD] Remove outdated backend whitelist for decode radix cache (#28238)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
This commit is contained in:
@@ -31,16 +31,10 @@ def handle_pd_disaggregation(server_args: "ServerArgs") -> None:
|
||||
"--disaggregation-decode-enable-radix-cache is incompatible "
|
||||
"with --enable-hisparse"
|
||||
)
|
||||
if server_args.disaggregation_transfer_backend not in (
|
||||
"nixl",
|
||||
"mooncake",
|
||||
"mori",
|
||||
):
|
||||
if server_args.disaggregation_transfer_backend == "fake":
|
||||
raise ValueError(
|
||||
"--disaggregation-decode-enable-radix-cache currently "
|
||||
"requires --disaggregation-transfer-backend in "
|
||||
"('nixl', 'mooncake', 'mori'), but got "
|
||||
f"{server_args.disaggregation_transfer_backend!r}"
|
||||
"--disaggregation-decode-enable-radix-cache is incompatible "
|
||||
"with --disaggregation-transfer-backend fake"
|
||||
)
|
||||
if server_args.speculative_algorithm is not None:
|
||||
raise ValueError(
|
||||
|
||||
@@ -7387,7 +7387,7 @@ class ServerArgs:
|
||||
parser.add_argument(
|
||||
"--disaggregation-decode-enable-radix-cache",
|
||||
action="store_true",
|
||||
help="Enable radix cache on decode server (PD mode). Caches KV prefixes to avoid redundant transfers. Requires --disaggregation-transfer-backend nixl, mooncake or mori and is incompatible with --enable-hisparse.",
|
||||
help="Enable radix cache on decode server (PD mode). Caches KV prefixes to avoid redundant transfers. Incompatible with --enable-hisparse, speculative decoding, and --disaggregation-transfer-backend fake.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--disaggregation-decode-enable-offload-kvcache",
|
||||
|
||||
Reference in New Issue
Block a user