mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
[Bugfix] use blockmanagerv1 for encoder-decoder (#9084)
Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
@ -903,6 +903,11 @@ class EngineArgs:
|
||||
"--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
|
||||
|
Reference in New Issue
Block a user