This commit is contained in:
Ryuichi Leo Takashige
2026-01-28 15:11:57 +00:00
parent bf67e7d334
commit ebe279018f
@@ -13,6 +13,7 @@ from mlx.nn.layers.distributed import (
shard_linear,
sum_gradients,
)
from mlx_lm.models.base import scaled_dot_product_attention
from mlx_lm.models.deepseek_v3 import DeepseekV3MLP
from mlx_lm.models.deepseek_v3 import Model as DeepseekV3Model
from mlx_lm.models.deepseek_v32 import DeepseekV32MLP