Skip to content

Commit

Permalink
fix order
Browse files Browse the repository at this point in the history
Signed-off-by: youkaichao <[email protected]>
  • Loading branch information
youkaichao committed Dec 10, 2024
1 parent d741330 commit 16d2a6d
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion vllm/v1/attention/backends/flash_attn.py
Original file line number Diff line number Diff line change
Expand Up @@ -50,13 +50,13 @@ class FlashAttentionMetadata:
# |-- query_len ---|

num_actual_tokens: int # Number of tokens excluding padding.
num_input_tokens: int = 0 # Number of tokens including padding.
max_query_len: int
query_start_loc: torch.Tensor
max_seq_len: int
seq_start_loc: torch.Tensor
block_table: torch.Tensor
slot_mapping: torch.Tensor
num_input_tokens: int = 0 # Number of tokens including padding.


class FlashAttentionImpl(AttentionImpl):
Expand Down

0 comments on commit 16d2a6d

Please sign in to comment.