squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixes an error in comment (#785)

Browse Source 
Signed-off-by: Tao He <sighingnow@gmail.com>
This commit is contained in:
Tao He 2024-01-24 04:38:29 +08:00 committed by GitHub
parent 197f2083a2
commit 204c3c6d1b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -212,7 +212,7 @@ def flash_attn_with_kvcache(
rotary_sin [optional]: (seqlen_ro, rotary_dim / 2). Similar to rotary_cos.
cache_seqlens: int, or (batch_size,), dtype torch.int32. The sequence lengths of the
KV cache.
block_table [optional]: (num_blocks, max_num_blocks_per_seq), dtype torch.int32.
block_table [optional]: (batch_size, max_num_blocks_per_seq), dtype torch.int32.
cache_batch_idx: (batch_size,), dtype torch.int32. The indices used to index into the KV cache.
If None, we assume that the batch indices are [0, 1, 2, ..., batch_size - 1].
If the indices are not distinct, and k and v are provided, the values updated in the cache

2
flash_attn/flash_attn_interface.py
View File

@ -1149,7 +1149,7 @@ def flash_attn_with_kvcache(
rotary_sin [optional]: (seqlen_ro, rotary_dim / 2). Similar to rotary_cos.
cache_seqlens: int, or (batch_size,), dtype torch.int32. The sequence lengths of the
KV cache.
block_table [optional]: (num_blocks, max_num_blocks_per_seq), dtype torch.int32.
block_table [optional]: (batch_size, max_num_blocks_per_seq), dtype torch.int32.
cache_batch_idx: (batch_size,), dtype torch.int32. The indices used to index into the KV cache.
If None, we assume that the batch indices are [0, 1, 2, ..., batch_size - 1].
If the indices are not distinct, and k and v are provided, the values updated in the cache