Skip to content

GitLab

Unverified Commit 80d93fd6 authored by pschlan-amd's avatar pschlan-amd Committed by GitHub
Browse files

gpu_model_runner: Cache is_encoder_decoder from model config (#35099) 


Signed-off-by: default avatarPatrick Schlangen <pschlan@amd.com>
parent ec853405
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/config/model.py
View file @ 80d93fd6
...@@ -1365,7 +1365,7 @@ class ModelConfig: ...@@ -1365,7 +1365,7 @@ class ModelConfig:
return diff_sampling_param return diff_sampling_param
@property @cached_property
def is_encoder_decoder(self) -> bool: def is_encoder_decoder(self) -> bool:
"""Extract the HF encoder/decoder model flag.""" """Extract the HF encoder/decoder model flag."""
return is_encoder_decoder(self.hf_config) return is_encoder_decoder(self.hf_config)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment