Improve streaming, log_level, memory report, weight loading, and benchmark script (#7632)
Co-authored-by: Kan Wu <wukanustc@gmail.com>
This commit is contained in:
@@ -99,6 +99,7 @@ class ServerArgs:
|
||||
log_level_http: Optional[str] = None
|
||||
log_requests: bool = False
|
||||
log_requests_level: int = 0
|
||||
crash_dump_folder: Optional[str] = None
|
||||
show_time_cost: bool = False
|
||||
enable_metrics: bool = False
|
||||
bucket_time_to_first_token: Optional[List[float]] = None
|
||||
@@ -927,8 +928,14 @@ class ServerArgs:
|
||||
"--log-requests-level",
|
||||
type=int,
|
||||
default=0,
|
||||
help="0: Log metadata. 1. Log metadata and partial input/output. 2. Log every input/output.",
|
||||
choices=[0, 1, 2],
|
||||
help="0: Log metadata (no sampling parameters). 1: Log metadata and sampling parameters. 2: Log metadata, sampling parameters and partial input/output. 3: Log every input/output.",
|
||||
choices=[0, 1, 2, 3],
|
||||
)
|
||||
parser.add_argument(
|
||||
"--crash-dump-folder",
|
||||
type=str,
|
||||
default=ServerArgs.crash_dump_folder,
|
||||
help="Folder path to dump requests from the last 5 min before a crash (if any). If not specified, crash dumping is disabled.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--show-time-cost",
|
||||
|
||||
Reference in New Issue
Block a user