mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[Feature] support mm disable_chunked (#4803)
* support mm disable_chunked * update code * update code * update code
This commit is contained in:
@@ -314,6 +314,10 @@ class EngineArgs:
|
||||
"""
|
||||
additional decode block num
|
||||
"""
|
||||
disable_chunked_mm_input: bool = False
|
||||
"""
|
||||
Disable chunked_mm_input for multi-model inference.
|
||||
"""
|
||||
|
||||
scheduler_name: str = "local"
|
||||
"""
|
||||
@@ -936,6 +940,13 @@ class EngineArgs:
|
||||
help="ports for rdma communication.",
|
||||
)
|
||||
|
||||
perf_group.add_argument(
|
||||
"--disable-chunked-mm-input",
|
||||
action="store_true",
|
||||
default=EngineArgs.disable_chunked_mm_input,
|
||||
help="Disable chunked mm input.",
|
||||
)
|
||||
|
||||
# Router parameters group
|
||||
router_group = parser.add_argument_group("Router")
|
||||
router_group.add_argument(
|
||||
|
||||
Reference in New Issue
Block a user