Skip to content

[Bugfix] use blockmanagerv1 for encoder-decoder #9084

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions vllm/engine/arg_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -903,6 +903,11 @@ def create_engine_config(self) -> EngineConfig:
"--enable-prefix-caching is currently not "
"supported for multimodal models and has been disabled.")
self.enable_prefix_caching = False
if model_config.is_encoder_decoder_model:
logger.warning(
"Block Manager v2 does not support encoder-decoder models"
" currently. Using Block Manager v1 as fallback.")
self.use_v2_block_manager = False

cache_config = CacheConfig(
block_size=self.block_size if self.device != "neuron" else
Expand Down
Loading