Clean up imports (#5467)

This commit is contained in:
Lianmin Zheng
2025-04-16 15:26:49 -07:00
committed by GitHub
parent d7bc19a46a
commit 177320a582
51 changed files with 376 additions and 573 deletions

View File

@@ -187,6 +187,7 @@ class ServerArgs:
n_share_experts_fusion: int = 0
disable_shared_experts_fusion: bool = False
disable_chunked_prefix_cache: bool = False
disable_fast_image_processor: bool = False
# Debug tensor dumps
debug_tensor_dump_output_folder: Optional[str] = None
@@ -198,9 +199,6 @@ class ServerArgs:
disaggregation_bootstrap_port: int = 8998
disaggregation_transfer_backend: str = "mooncake"
# multimodal
disable_fast_image_processor: bool = False
def __post_init__(self):
# Expert parallelism
if self.enable_ep_moe:
@@ -1136,6 +1134,11 @@ class ServerArgs:
action="store_true",
help="Disable chunked prefix cache feature for deepseek, which should save overhead for short sequences.",
)
parser.add_argument(
"--disable-fast-image-processor",
action="store_true",
help="Adopt base image processor instead of fast image processor.",
)
# Server warmups
parser.add_argument(
@@ -1187,13 +1190,6 @@ class ServerArgs:
help="The backend for disaggregation transfer. Default is mooncake.",
)
# Multimodal
parser.add_argument(
"--disable-fast-image-processor",
action="store_true",
help="Adopt base image processor instead of fast image processor.",
)
@classmethod
def from_cli_args(cls, args: argparse.Namespace):
args.tp_size = args.tensor_parallel_size