Tree: Format

common/args.py

@@ -85,7 +85,7 @@ def add_model_args(parser: argparse.ArgumentParser):
     model_group.add_argument(
         "--cache-size",
         type=int,
-        help="The size of the prompt cache (in number of tokens) to allocate"
+        help="The size of the prompt cache (in number of tokens) to allocate",
     )
     model_group.add_argument(
         "--rope-scale", type=float, help="Sets rope_scale or compress_pos_emb"

endpoints/OAI/types/model.py

@@ -74,9 +74,7 @@ class ModelLoadRequest(BaseModel):
         examples=[4096],
     )
     cache_size: Optional[int] = Field(
-        description=(
-            "Number in tokens, must be greater than or equal to max_seq_len"
-        ),
+        description=("Number in tokens, must be greater than or equal to max_seq_len"),
         default=None,
         examples=[4096],
     )