zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-06-24 09:21:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix causal mask sdpa vec (#2053)

Browse Source 
* fix sdpa vector causal mask

* test
This commit is contained in:
Awni Hannun 2025-04-08 09:11:23 -07:00 committed by GitHub
parent 08a1bf3f10
commit 00794c42bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mlx/backend/metal/scaled_dot_product_attention.cpp
View File

@ -172,6 +172,7 @@ void sdpa_vector(
std::string hash_name = kname;
hash_name += has_mask ? "_mask" : "_nomask";
hash_name += query_transposed ? "_qt" : "_qnt";
hash_name += do_causal ? "_c" : "_nc";
// Get the kernel
auto& compute_encoder = d.get_command_encoder(s.index);
@ -268,6 +269,7 @@ void sdpa_vector_2pass(
std::string hash_name = kname;
hash_name += has_mask ? "_mask" : "_nomask";
hash_name += query_transposed ? "_qt" : "_qnt";
hash_name += do_causal ? "_c" : "_nc";
// Get the kernel
auto& compute_encoder = d.get_command_encoder(s.index);

5
python/tests/test_fast_sdpa.py
View File

@ -347,6 +347,7 @@ class TestFastSDPA(mlx_tests.MLXTestCase):
)
masks = [
None,
mx.array(True),
mx.array([True] * (L - 10) + [False] * 10),
mx.random.uniform(shape=(Nq, 1, L)) > 0.2,
@ -392,7 +393,7 @@ class TestFastSDPA(mlx_tests.MLXTestCase):
def test_fast_sdpa_few_query(self):
D = 64
L = 43
Lq = 4
Lq = 8
Nq = 8
Nkv = 1
scale = 1.0
@ -403,6 +404,7 @@ class TestFastSDPA(mlx_tests.MLXTestCase):
v = 5e-1 * mx.random.normal(shape=(1, Nkv, L, D))
masks = [
None,
mx.array(True),
mx.array([True] * (L - 10) + [False] * 10),
mx.random.uniform(shape=(Nq, 1, L)) > 0.2,
@ -428,6 +430,7 @@ class TestFastSDPA(mlx_tests.MLXTestCase):
v = 5e-1 * mx.random.normal(shape=(1, Nkv, L, D))
masks = [
None,
mx.array(True),
mx.array([True] * (L - 10) + [False] * 10),
mx.random.uniform(shape=(Nq, 1, L)) > 0.2,