Replace head_mapping params with num_kv_heads to attention kernel. (#1997)
Co-authored-by: wangguoya <wangguoya@baidu.com> Co-authored-by: Yang Zhao <zhaoyangstar@foxmail.com>
This commit is contained in:
co-authored by
wangguoya
Yang Zhao
parent
24cde76a15
commit
dacaf5a400
+2
-2
@@ -5,7 +5,7 @@ void paged_attention_v1(
|
||||
torch::Tensor& query,
|
||||
torch::Tensor& key_cache,
|
||||
torch::Tensor& value_cache,
|
||||
torch::Tensor& head_mapping,
|
||||
int num_kv_heads,
|
||||
float scale,
|
||||
torch::Tensor& block_tables,
|
||||
torch::Tensor& context_lens,
|
||||
@@ -21,7 +21,7 @@ void paged_attention_v2(
|
||||
torch::Tensor& query,
|
||||
torch::Tensor& key_cache,
|
||||
torch::Tensor& value_cache,
|
||||
torch::Tensor& head_mapping,
|
||||
int num_kv_heads,
|
||||
float scale,
|
||||
torch::Tensor& block_tables,
|
||||
torch::Tensor& context_lens,
|
||||
|
||||
Reference in New Issue
Block a user