Unverified Commit 68fcaa22 authored by Xuanlei Zhao's avatar Xuanlei Zhao Committed by GitHub
Browse files

remove duplicate import (#5100)

parent e53e729d
......@@ -413,8 +413,6 @@ def get_llama_flash_attention_forward():
warnings.warn("using llamav1, llamav1 hasn't repeat_kv function")
llama_version = 1
from colossalai.kernel.cuda_native import AttnMaskType, ColoAttention
def forward(
self: LlamaAttention,
hidden_states: torch.Tensor,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment