mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
supports internode_ll_two_stage (#4162)
* supports internode_ll_two_stage * supports internode_ll_two_stage * supports internode_ll_two_stage * supports internode_ll_two_stage * supports D internode_ll_two_stage * fix codestype * fix xpu internode_ll_two_stage * fix xpu internode_ll_two_stage
This commit is contained in:
@@ -636,6 +636,11 @@ def parse_args():
|
||||
action="store_true",
|
||||
help="enable chunked prefill",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--use_internode_ll_two_stage",
|
||||
action="store_true",
|
||||
help="enable internode_ll_two_stage",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--speculative_config",
|
||||
type=json.loads,
|
||||
|
||||
Reference in New Issue
Block a user