mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-28 10:51:39 +08:00
[Fearture] Support mm model close prefix cache (#4502)
* support mm prefix cache close * add * fix * fix * fix --------- Co-authored-by: ltd0924 <luotingdan@baidu.com>
This commit is contained in:
@@ -20,6 +20,17 @@ from fastdeploy.utils import get_logger
|
||||
|
||||
logger = get_logger("prefix_cache_manager", "prefix_cache_manager.log")
|
||||
|
||||
DISABLE_PREFIX_CACHE_MM_MODEL: set[str] = {
|
||||
"Ernie5ForCausalLM",
|
||||
}
|
||||
|
||||
|
||||
def is_mm_model_disable_prefix_cache(model_arch):
|
||||
"""
|
||||
check if the model architecture is in DISABLE_PREFIX_CACHE_MM_MODEL
|
||||
"""
|
||||
return model_arch in DISABLE_PREFIX_CACHE_MM_MODEL
|
||||
|
||||
|
||||
class CacheStatus(Enum):
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user