Skip to content

Refactor modeling tests #482

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yzhangcs merged 5 commits into from
Jun 24, 2025
Merged

Refactor modeling tests #482

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
679fc11
Refactor modeling tests
yzhangcs Jun 24, 2025
8502d22
[CI] Enable verbose output
yzhangcs Jun 24, 2025
8238ded
Include `dtype` in `run_test_model_forward_backward` calls
yzhangcs Jun 24, 2025
540fe57
Refactor variable length constant name and update test parameter order
yzhangcs Jun 24, 2025
d5c7aa2
only headdim 32/64
yzhangcs Jun 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 37 additions & 15 deletions tests/models/test_modeling_abc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,47 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [4])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype', 'use_l2warp'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
(4, 4, 1024, 4, 128, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
run_test_model_forward_backward(L, B, T, H, D, ABCConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, ABCConfig, dtype)
52 changes: 37 additions & 15 deletions tests/models/test_modeling_bitnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,47 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [4])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'use_l2warp', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
(4, 4, 1024, 4, 128, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
run_test_model_forward_backward(L, B, T, H, D, BitNetConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, BitNetConfig, dtype)
52 changes: 37 additions & 15 deletions tests/models/test_modeling_comba.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,47 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [4])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'use_l2warp', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
(4, 4, 1024, 4, 128, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
Comment thread
coderabbitai[bot] marked this conversation as resolved.
run_test_model_forward_backward(L, B, T, H, D, CombaConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, CombaConfig, dtype)
52 changes: 37 additions & 15 deletions tests/models/test_modeling_deltanet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,47 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [4])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'use_l2warp', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
(4, 4, 1024, 4, 128, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
run_test_model_forward_backward(L, B, T, H, D, DeltaNetConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, DeltaNetConfig, dtype)
52 changes: 37 additions & 15 deletions tests/models/test_modeling_forgetting_transformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,47 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [4])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'use_l2warp', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
(4, 4, 1024, 4, 128, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
run_test_model_forward_backward(L, B, T, H, D, ForgettingTransformerConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, ForgettingTransformerConfig, dtype)
51 changes: 36 additions & 15 deletions tests/models/test_modeling_gated_deltanet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,46 @@
# ===================================================================================
# Test for Modeling (Forward/Backward Pass)
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [1024])
@pytest.mark.parametrize("H", [4])
@pytest.mark.parametrize("D", [64, 128])
@pytest.mark.parametrize("dtype", [torch.bfloat16])
@pytest.mark.parametrize("use_l2warp", [True, False])
def test_modeling(L, B, T, H, D, dtype, use_l2warp):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'use_l2warp', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-use_l2warp{}-{}".format(*test))
for test in [
(4, 4, 1024, 4, 64, True, torch.bfloat16),
(4, 4, 1024, 4, 64, False, torch.bfloat16),
]
]
)
def test_modeling(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
use_l2warp: bool,
):
Comment thread
yzhangcs marked this conversation as resolved.
run_test_model_forward_backward(L, B, T, H, D, GatedDeltaNetConfig, dtype, use_l2warp)


# ===================================================================================
# Test for Generation
# ===================================================================================
@pytest.mark.parametrize("L", [2])
@pytest.mark.parametrize("B", [4])
@pytest.mark.parametrize("T", [4000])
@pytest.mark.parametrize("H", [8])
@pytest.mark.parametrize("D", [64])
@pytest.mark.parametrize("dtype", [torch.float16])
def test_generation(L, B, T, H, D, dtype):
@pytest.mark.parametrize(
['L', 'B', 'T', 'H', 'D', 'dtype'],
[
pytest.param(*test, id="L{}-B{}-T{}-H{}-D{}-{}".format(*test))
for test in [
(2, 4, 2000, 8, 64, torch.float16),
]
]
)
def test_generation(
L: int,
B: int,
T: int,
H: int,
D: int,
dtype: torch.dtype,
):
run_test_generation(L, B, T, H, D, GatedDeltaNetConfig, dtype)
Loading
Loading