Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
## Summary
Update CONTRIBUTING.md to cover corner cases.
<!---
## Details
This is an optional section; is there anything specific that reviewers
should be aware of?
--->
## Testing Done
<!--- This is a required section; please describe how this change was
tested. --->
In RTX3070,
```
❯ export PYTHONPATH="${PYTHONPATH}:/mnt/d/ML/fork/Liger-Kernel"
❯ make test
pytest --disable-warnings test/ --ignore=test/convergence
=================================================================================================== test session starts ====================================================================================================
platform linux -- Python 3.11.7, pytest-8.2.1, pluggy-1.5.0
rootdir: /mnt/d/ML/fork/Liger-Kernel
collected 114 items
test/transformers/test_cross_entropy.py .FF.FFF.FFF.FFFFFFFFFFFF.FF.FFF..FF.FFF.FFFFFFFFFFF.FFF.FF [ 50%]
test/transformers/test_fused_linear_cross_entropy.py ....FF [ 56%]
test/transformers/test_geglu.py F....... [ 63%]
test/transformers/test_rms_norm.py ................ [ 77%]
test/transformers/test_rope.py ............ [ 87%]
test/transformers/test_swiglu.py ........ [ 94%]
test/transformers/test_trainer_integration.py ... [ 97%]
test/transformers/test_transformers_monkey_patch.py . [ 98%]
test/triton/test_triton_monkey_patch.py .. [100%]
==================================================================================== FAILURES =====================================================================================
______________________________________________________________ test_correctness[0.1-dtype0-1e-08-0.05-8-4096-32000] _______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 0.1, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 0.1, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
_tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
_input = _tensor.detach().clone().requires_grad_(True)
_input2 = _tensor.detach().clone().requires_grad_(True)
target = torch.randint(0, V, (B * T,), device="cuda", dtype=torch.long)
output = torch_ce(_input, target)
output2 = target_ce(_input2, target)
assert torch.allclose(output, output2, atol=atol, rtol=rtol)
output.backward()
output2.backward()
> assert torch.allclose(_input.grad, _input2.grad, atol=atol, rtol=rtol)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 12.70 GiB is allocated by PyTorch, and 1001.75 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:26: OutOfMemoryError
______________________________________________________________ test_correctness[0.1-dtype0-1e-08-0.05-4-4096-128256] ______________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 0.1, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 0.1, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 11.73 GiB is allocated by PyTorch, and 1.75 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype1-1e-08-0.05-4-4096-32000] _______________________________________________________________
B = 4, T = 4096, V = 32000, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 32000, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
_tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
_input = _tensor.detach().clone().requires_grad_(True)
_input2 = _tensor.detach().clone().requires_grad_(True)
target = torch.randint(0, V, (B * T,), device="cuda", dtype=torch.long)
output = torch_ce(_input, target)
output2 = target_ce(_input2, target)
assert torch.allclose(output, output2, atol=atol, rtol=rtol)
output.backward()
output2.backward()
> assert torch.allclose(_input.grad, _input2.grad, atol=atol, rtol=rtol)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1000.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.18 GiB is allocated by PyTorch, and 509.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:26: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype1-1e-08-0.05-8-4096-32000] _______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 11.72 GiB is allocated by PyTorch, and 1009.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype1-1e-08-0.05-4-4096-128256] ______________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 1.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 11.72 GiB is allocated by PyTorch, and 1009.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[10.0-dtype2-1e-08-0.05-4-4096-32000] ______________________________________________________________
B = 4, T = 4096, V = 32000, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 32000, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
_tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
_input = _tensor.detach().clone().requires_grad_(True)
> _input2 = _tensor.detach().clone().requires_grad_(True)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1000.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.67 GiB is allocated by PyTorch, and 9.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:16: OutOfMemoryError
______________________________________________________________ test_correctness[10.0-dtype2-1e-08-0.05-8-4096-32000] ______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.67 GiB is allocated by PyTorch, and 9.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
_____________________________________________________________ test_correctness[10.0-dtype2-1e-08-0.05-4-4096-128256] ______________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 10.0, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 11.73 GiB is allocated by PyTorch, and 1.75 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[0.1-dtype3-1e-08-1e-06-4-4096-32000] ______________________________________________________________
B = 4, T = 4096, V = 32000, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
test/transformers/test_cross_entropy.py:20: in _test_correctness_once
output = torch_ce(_input, target)
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/nn/modules/module.py:1511: in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/nn/modules/module.py:1520: in _call_impl
return forward_call(*args, **kwargs)
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/nn/modules/loss.py:1179: in forward
return F.cross_entropy(input, target, weight=self.weight,
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
input = tensor([[-0.0925, -0.0425, -0.2644, ..., 0.0010, 0.1883, -0.0227],
[ 0.0096, -0.0009, -0.0456, ..., 0.062...98],
[ 0.1096, 0.1418, -0.0479, ..., -0.0130, 0.0280, -0.0784]],
device='cuda:0', requires_grad=True)
target = tensor([11911, 6795, 20998, ..., 13584, 24371, 414], device='cuda:0'), weight = None, size_average = None, ignore_index = -100, reduce = None, reduction = 'mean'
label_smoothing = 0.0
def cross_entropy(
input: Tensor,
target: Tensor,
weight: Optional[Tensor] = None,
size_average: Optional[bool] = None,
ignore_index: int = -100,
reduce: Optional[bool] = None,
reduction: str = "mean",
label_smoothing: float = 0.0,
) -> Tensor:
r"""Compute the cross entropy loss between input logits and target.
See :class:`~torch.nn.CrossEntropyLoss` for details.
Args:
input (Tensor) : Predicted unnormalized logits;
see Shape section below for supported shapes.
target (Tensor) : Ground truth class indices or class probabilities;
see Shape section below for supported shapes.
weight (Tensor, optional): a manual rescaling weight given to each
class. If given, has to be a Tensor of size `C`
size_average (bool, optional): Deprecated (see :attr:`reduction`). By default,
the losses are averaged over each loss element in the batch. Note that for
some losses, there multiple elements per sample. If the field :attr:`size_average`
is set to ``False``, the losses are instead summed for each minibatch. Ignored
when reduce is ``False``. Default: ``True``
ignore_index (int, optional): Specifies a target value that is ignored
and does not contribute to the input gradient. When :attr:`size_average` is
``True``, the loss is averaged over non-ignored targets. Note that
:attr:`ignore_index` is only applicable when the target contains class indices.
Default: -100
reduce (bool, optional): Deprecated (see :attr:`reduction`). By default, the
losses are averaged or summed over observations for each minibatch depending
on :attr:`size_average`. When :attr:`reduce` is ``False``, returns a loss per
batch element instead and ignores :attr:`size_average`. Default: ``True``
reduction (str, optional): Specifies the reduction to apply to the output:
``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied,
``'mean'``: the sum of the output will be divided by the number of
elements in the output, ``'sum'``: the output will be summed. Note: :attr:`size_average`
and :attr:`reduce` are in the process of being deprecated, and in the meantime,
specifying either of those two args will override :attr:`reduction`. Default: ``'mean'``
label_smoothing (float, optional): A float in [0.0, 1.0]. Specifies the amount
of smoothing when computing the loss, where 0.0 means no smoothing. The targets
become a mixture of the original ground truth and a uniform distribution as described in
`Rethinking the Inception Architecture for Computer Vision <https://arxiv.org/abs/1512.00567>`__. Default: :math:`0.0`.
Shape:
- Input: Shape :math:`(C)`, :math:`(N, C)` or :math:`(N, C, d_1, d_2, ..., d_K)` with :math:`K \geq 1`
in the case of `K`-dimensional loss.
- Target: If containing class indices, shape :math:`()`, :math:`(N)` or :math:`(N, d_1, d_2, ..., d_K)` with
:math:`K \geq 1` in the case of K-dimensional loss where each value should be between :math:`[0, C)`.
If containing class probabilities, same shape as the input and each value should be between :math:`[0, 1]`.
where:
.. math::
\begin{aligned}
C ={} & \text{number of classes} \\
N ={} & \text{batch size} \\
\end{aligned}
Examples::
>>> # Example of target with class indices
>>> input = torch.randn(3, 5, requires_grad=True)
>>> target = torch.randint(5, (3,), dtype=torch.int64)
>>> loss = F.cross_entropy(input, target)
>>> loss.backward()
>>>
>>> # Example of target with class probabilities
>>> input = torch.randn(3, 5, requires_grad=True)
>>> target = torch.randn(3, 5).softmax(dim=1)
>>> loss = F.cross_entropy(input, target)
>>> loss.backward()
"""
if has_torch_function_variadic(input, target, weight):
return handle_torch_function(
cross_entropy,
(input, target, weight),
input,
target,
weight=weight,
size_average=size_average,
ignore_index=ignore_index,
reduce=reduce,
reduction=reduction,
label_smoothing=label_smoothing,
)
if size_average is not None or reduce is not None:
reduction = _Reduction.legacy_get_string(size_average, reduce)
> return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.67 GiB is allocated by PyTorch, and 9.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/nn/functional.py:3059: OutOfMemoryError
______________________________________________________________ test_correctness[0.1-dtype3-1e-08-1e-06-8-4096-32000] ______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.67 GiB is allocated by PyTorch, and 9.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
_____________________________________________________________ test_correctness[0.1-dtype3-1e-08-1e-06-4-4096-128256] ______________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 7.83 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.67 GiB is allocated by PyTorch, and 9.62 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[0.1-dtype3-1e-08-1e-06-3-423-32000] _______________________________________________________________
B = 3, T = 423, V = 32000, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 3, T = 423, V = 32000, scalar = 0.1, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
_tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
_input = _tensor.detach().clone().requires_grad_(True)
_input2 = _tensor.detach().clone().requires_grad_(True)
target = torch.randint(0, V, (B * T,), device="cuda", dtype=torch.long)
output = torch_ce(_input, target)
output2 = target_ce(_input2, target)
assert torch.allclose(output, output2, atol=atol, rtol=rtol)
output.backward()
output2.backward()
> assert torch.allclose(_input.grad, _input2.grad, atol=atol, rtol=rtol)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 156.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.47 GiB is allocated by PyTorch, and 132.35 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:26: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype4-1e-08-1e-06-4-4096-32000] ______________________________________________________________
B = 4, T = 4096, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.28 GiB is allocated by PyTorch, and 13.98 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype4-1e-08-1e-06-8-4096-32000] ______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.28 GiB is allocated by PyTorch, and 13.98 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
_____________________________________________________________ test_correctness[1.0-dtype4-1e-08-1e-06-4-4096-128256] ______________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 7.83 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.28 GiB is allocated by PyTorch, and 13.98 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[1.0-dtype4-1e-08-1e-06-3-423-32000] _______________________________________________________________
B = 3, T = 423, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 3, T = 423, V = 32000, scalar = 1.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
_tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
_input = _tensor.detach().clone().requires_grad_(True)
> _input2 = _tensor.detach().clone().requires_grad_(True)
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 156.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.58 GiB is allocated by PyTorch, and 16.17 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:16: OutOfMemoryError
_____________________________________________________________ test_correctness[10.0-dtype5-1e-08-1e-06-4-4096-32000] ______________________________________________________________
B = 4, T = 4096, V = 32000, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 32000, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.95 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.97 GiB is allocated by PyTorch, and 11.81 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
_____________________________________________________________ test_correctness[10.0-dtype5-1e-08-1e-06-8-4096-32000] ______________________________________________________________
B = 8, T = 4096, V = 32000, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 8, T = 4096, V = 32000, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 3.91 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.97 GiB is allocated by PyTorch, and 11.81 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
_____________________________________________________________ test_correctness[10.0-dtype5-1e-08-1e-06-4-4096-128256] _____________________________________________________________
B = 4, T = 4096, V = 128256, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
target_ce = LigerCrossEntropyLoss(), B = 4, T = 4096, V = 128256, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
def _test_correctness_once(target_ce, B, T, V, scalar, dtype, atol, rtol):
torch.manual_seed(0)
torch_ce = CrossEntropyLoss()
> _tensor = torch.randn(B * T, V, device="cuda", dtype=dtype) * scalar
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 7.83 GiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 13.97 GiB is allocated by PyTorch, and 11.81 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
test/transformers/test_cross_entropy.py:14: OutOfMemoryError
______________________________________________________________ test_correctness[10.0-dtype5-1e-08-1e-06-3-423-32000] ______________________________________________________________
B = 3, T = 423, V = 32000, scalar = 10.0, dtype = torch.float32, atol = 1e-08, rtol = 1e-06
@pytest.mark.parametrize(
"B, T, V",
[
(4, 4096, 32000), # llama2, mistral
(8, 4096, 32000), # llama2, mistral
(4, 4096, 128256), # llama3
# # weird shapes
(3, 423, 32000),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness(B, T, V, scalar, dtype, atol, rtol):
liger_ce = LigerCrossEntropyLoss()
> _test_correctness_once(liger_ce, B, T, V, scalar, dtype, atol, rtol)
test/transformers/test_cross_entropy.py:112:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
test/transformers/test_cross_entropy.py:24: in _test_correctness_once
output.backward()
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/_tensor.py:522: in backward
torch.autograd.backward(
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
tensors = (tensor(41.5440, device='cuda:0', grad_fn=<NllLossBackward0>),), grad_tensors = None, retain_graph = False, create_graph = False, grad_variables = None, inputs = ()
def backward(
tensors: _TensorOrTensors,
grad_tensors: Optional[_TensorOrTensors] = None,
retain_graph: Optional[bool] = None,
create_graph: bool = False,
grad_variables: Optional[_TensorOrTensors] = None,
inputs: Optional[_TensorOrTensorsOrGradEdge] = None,
) -> None:
r"""Computes the sum of gradients of given tensors with respect to graph
leaves.
The graph is differentiated using the chain rule. If any of ``tensors``
are non-scalar (i.e. their data has more than one element) and require
gradient, then the Jacobian-vector product would be computed, in this
case the function additionally requires specifying ``grad_tensors``.
It should be a sequence of matching length, that contains the "vector"
in the Jacobian-vector product, usually the gradient of the differentiated
function w.r.t. corresponding tensors (``None`` is an acceptable value for
all tensors that don't need gradient tensors).
This function accumulates gradients in the leaves - you might need to zero
``.grad`` attributes or set them to ``None`` before calling it.
See :ref:`Default gradient layouts<default-grad-layouts>`
for details on the memory layout of accumulated gradients.
.. note::
Using this method with ``create_graph=True`` will create a reference cycle
between the parameter and its gradient which can cause a memory leak.
We recommend using ``autograd.grad`` when creating the graph to avoid this.
If you have to use this function, make sure to reset the ``.grad`` fields of your
parameters to ``None`` after use to break the cycle and avoid the leak.
.. note::
If you run any forward ops, create ``grad_tensors``, and/or call ``backward``
in a user-specified CUDA stream context, see
:ref:`Stream semantics of backward passes<bwd-cuda-stream-semantics>`.
.. note::
When ``inputs`` are provided and a given input is not a leaf,
the current implementation will call its grad_fn (even though it is not strictly needed to get this gradients).
It is an implementation detail on which the user should not rely.
See https://github.com/pytorch/pytorch/pull/60521#issuecomment-867061780 for more details.
Args:
tensors (Sequence[Tensor] or Tensor): Tensors of which the derivative will be
computed.
grad_tensors (Sequence[Tensor or None] or Tensor, optional): The "vector" in
the Jacobian-vector product, usually gradients w.r.t. each element of
corresponding tensors. None values can be specified for scalar Tensors or
ones that don't require grad. If a None value would be acceptable for all
grad_tensors, then this argument is optional.
retain_graph (bool, optional): If ``False``, the graph used to compute the grad
will be freed. Note that in nearly all cases setting this option to ``True``
is not needed and often can be worked around in a much more efficient
way. Defaults to the value of ``create_graph``.
create_graph (bool, optional): If ``True``, graph of the derivative will
be constructed, allowing to compute higher order derivative products.
Defaults to ``False``.
inputs (Sequence[Tensor] or Tensor or Sequence[GradientEdge], optional): Inputs w.r.t. which the gradient
be will accumulated into ``.grad``. All other Tensors will be ignored. If
not provided, the gradient is accumulated into all the leaf Tensors that
were used to compute the attr::tensors.
"""
if torch._C._are_functorch_transforms_active():
raise RuntimeError(
"backward() called inside a functorch transform. This is not "
"supported, please use functorch.grad or functorch.vjp instead "
"or call backward() outside of functorch transforms."
)
if grad_variables is not None:
warnings.warn("'grad_variables' is deprecated. Use 'grad_tensors' instead.")
if grad_tensors is None:
grad_tensors = grad_variables
else:
raise RuntimeError(
"'grad_tensors' and 'grad_variables' (deprecated) "
"arguments both passed to backward(). Please only "
"use 'grad_tensors'."
)
if inputs is not None and len(inputs) == 0:
raise RuntimeError("'inputs' argument to backward() cannot be empty.")
tensors = (tensors,) if isinstance(tensors, torch.Tensor) else tuple(tensors)
inputs = (
(inputs,)
if isinstance(inputs, (torch.Tensor, graph.GradientEdge))
else tuple(inputs)
if inputs is not None
else tuple()
)
grad_tensors_ = _tensor_or_tensors_to_tuple(grad_tensors, len(tensors))
grad_tensors_ = _make_grads(tensors, grad_tensors_, is_grads_batched=False)
if retain_graph is None:
retain_graph = create_graph
# The reason we repeat the same comment below is that
# some Python versions print out the first line of a multi-line function
# calls in the traceback and some print out the last line
> Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
tensors,
grad_tensors_,
retain_graph,
create_graph,
inputs,
allow_unreachable=True,
accumulate_grad=True,
) # Calls into the C++ engine to run the backward pass
E torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 156.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 14.58 GiB is allocated by PyTorch, and 16.17 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
/home/lancerts/miniconda3/envs/wsl-dev/lib/python3.11/site-packages/torch/autograd/__init__.py:266: OutOfMemoryError
____________________________________________________ test_correctness_with_ignore_index[0.1-dtype0-1e-08-0.05-8-4096-32000-2] _____________________________________________________
B = 8, T = 4096, V = 32000, ignore_index = 2, scalar = 0.1, dtype = torch.bfloat16, atol = 1e-08, rtol = 0.05
@pytest.mark.parametrize(
"B, T, V, ignore_index",
[
(4, 4096, 32000, -100), # llama2, mistral
(8, 4096, 32000, 2), # llama2, mistral
(4, 4096, 128256, -300), # llama3
# weird shapes
(3, 423, 32000, -123),
],
)
@pytest.mark.parametrize(
"scalar, dtype, atol, rtol",
[
(0.1, torch.bfloat16, 1e-8, 5e-2),
(1.0, torch.bfloat16, 1e-8, 5e-2),
(10.0, torch.bfloat16, 1e-8, 5e-2),
(0.1, torch.float32, 1e-8, 1e-6),
(1.0, torch.float32, 1e-8, 1e-6),
(10.0, torch.float32, 1e-8, 1e-6),
],
)
def test_correctness_with_ignore_index(
…- Loading branch information
