mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Feature][Executor] GPU Model Runner Supports prompt_logprobs and max_logprobs (#4769)
This commit is contained in:
@@ -551,6 +551,7 @@ class LLMEngine:
|
||||
f" --convert {self.cfg.model_config.convert}"
|
||||
f" --override-pooler-config {self.cfg.model_config.override_pooler_config}"
|
||||
f" --logprobs_mode {self.cfg.model_config.logprobs_mode}"
|
||||
f" --max_logprobs {self.cfg.model_config.max_logprobs}"
|
||||
)
|
||||
if self.cfg.structured_outputs_config.logits_processors is not None:
|
||||
arguments += f" --logits-processors {' '.join(self.cfg.structured_outputs_config.logits_processors)}"
|
||||
|
||||
Reference in New Issue
Block a user