Support S3 Sharded loading with RunAI Model Streamer (#16317)
Signed-off-by: Omer Dayan (SW-GPU) <omer@run.ai> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
@@ -1489,6 +1489,7 @@ class LoadFormat(str, enum.Enum):
|
||||
BITSANDBYTES = "bitsandbytes"
|
||||
MISTRAL = "mistral"
|
||||
RUNAI_STREAMER = "runai_streamer"
|
||||
RUNAI_STREAMER_SHARDED = "runai_streamer_sharded"
|
||||
FASTSAFETENSORS = "fastsafetensors"
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user