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

[Docs] Fix docstring about Q nheads being divisible by KV nheads

Browse Source
This commit is contained in:
Tri Dao 2023-07-31 17:47:03 -07:00
parent a4f148b6ab
commit 8f4cd4c16b
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
flash_attn/flash_attn_interface.py
View File

@ -316,7 +316,7 @@ def flash_attn_kvpacked_func(q, kv, dropout_p=0.0, softmax_scale=None, causal=Fa
calling flash_attn_func on Q, K, V since the backward pass avoids explicit concatenation
of the gradients of K, V.
Supports multi-query and grouped-query attention (MQA/GQA) by passing in KV with fewer heads
than Q. Note that the number of heads in KV must be divisible by the number of heads in Q.
than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.
@ -346,7 +346,7 @@ def flash_attn_func(q, k, v, dropout_p=0.0, softmax_scale=None, causal=False,
return_attn_probs=False):
"""dropout_p should be set to 0.0 during evaluation
Supports multi-query and grouped-query attention (MQA/GQA) by passing in KV with fewer heads
than Q. Note that the number of heads in KV must be divisible by the number of heads in Q.
than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.
@ -416,7 +416,7 @@ def flash_attn_varlen_kvpacked_func(q, kv, cu_seqlens_q, cu_seqlens_k, max_seqle
calling flash_attn_func on Q, K, V since the backward pass avoids explicit concatenation
of the gradients of K, V.
Supports multi-query and grouped-query attention (MQA/GQA) by passing in KV with fewer heads
than Q. Note that the number of heads in KV must be divisible by the number of heads in Q.
than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.
@ -456,7 +456,7 @@ def flash_attn_varlen_func(q, k, v, cu_seqlens_q, cu_seqlens_k, max_seqlen_q, ma
return_attn_probs=False):
"""dropout_p should be set to 0.0 during evaluation
Supports multi-query and grouped-query attention (MQA/GQA) by passing in K, V with fewer heads
than Q. Note that the number of heads in K, V must be divisible by the number of heads in Q.
than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.