merge upstream develop

2023-10-09 21:35:52 +08:00 · 2023-10-09 21:35:52 +08:00 · 1b7935dd98
parent a8dea6313f
commit 1b7935dd98
1 changed files with 1 additions and 0 deletions
--- a/internlm/model/multi_head_attention.py
+++ b/internlm/model/multi_head_attention.py
@ -6,6 +6,7 @@ from typing import Any, Optional, Tuple

 import torch
 import torch.distributed as dist
+import torch.nn.functional as F
 from einops import rearrange
 from flash_attn.modules.mha import (
    CrossAttention,