mirror of
https://github.com/ml-explore/mlx.git
synced 2025-12-16 01:49:05 +08:00
Fused attention for single query (#1497)
This commit is contained in:
committed by
GitHub
parent
9dd72cd421
commit
50d8bed468
@@ -30,8 +30,9 @@ build_kernel(layer_norm)
|
||||
build_kernel(random)
|
||||
build_kernel(rms_norm)
|
||||
build_kernel(rope)
|
||||
build_kernel(scaled_dot_product_attention scaled_dot_product_attention_params.h
|
||||
steel/defines.h steel/gemm/transforms.h steel/utils.h)
|
||||
build_kernel(
|
||||
scaled_dot_product_attention scaled_dot_product_attention_params.h
|
||||
sdpa_vector.h steel/defines.h steel/gemm/transforms.h steel/utils.h)
|
||||
|
||||
set(STEEL_HEADERS
|
||||
steel/defines.h
|
||||
|
||||
Reference in New Issue
Block a user