mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[Feature][Executor] GPU Model Runner Supports prompt_logprobs and max_logprobs (#4769)
This commit is contained in:
@@ -736,6 +736,12 @@ def parse_args():
|
||||
action="store_true",
|
||||
help="Enable output of token-level log probabilities.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--max_logprobs",
|
||||
type=int,
|
||||
default=20,
|
||||
help="Maximum number of log probabilities.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--logprobs_mode",
|
||||
type=str,
|
||||
|
||||
Reference in New Issue
Block a user