Improve streaming, log_level, memory report, weight loading, and benchmark script (#7632)

Co-authored-by: Kan Wu <wukanustc@gmail.com>
2025-06-29 23:16:19 -07:00
parent c5131f7a2f
commit 22352d47a9
24 changed files with 626 additions and 160 deletions
@@ -13,7 +13,7 @@
 # ==============================================================================
 """Inference-only Mistral model."""

-from typing import List, Union
+from typing import List

 import torch
 from transformers.models.mistral3.modeling_mistral3 import Mistral3MultiModalProjector