zijie-tian/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[fix] Fix import error.

Browse Source
This commit is contained in:
Zijie Tian
2025-12-11 05:31:06 +08:00
parent babfa17354
commit b9ed77cbbb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
nanovllm/kvcache/chunked_attention.py
View File

@@ -499,7 +499,7 @@ class ChunkedPrefillState:
# Test function # Test function
def _test_chunked_attention(): def _test_chunked_attention():
"""Test chunked attention correctness against full attention.""" """Test chunked attention correctness against full attention."""
from flash_attn import flash_attn_func from flash_attn.flash_attn_interface import flash_attn_func
torch.manual_seed(42) torch.manual_seed(42)