e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
111 lines
3.0 KiB
Python
111 lines
3.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""
|
|
Test the piecewise compilation with a simple model so that we
|
|
can exactly calculate the expected output and side effects.
|
|
"""
|
|
|
|
import torch
|
|
from torch import nn
|
|
from torch.library import Library
|
|
|
|
from vllm.compilation.counter import compilation_counter
|
|
from vllm.compilation.decorators import support_torch_compile
|
|
from vllm.config import (CompilationConfig, CompilationLevel, VllmConfig,
|
|
set_current_vllm_config)
|
|
from vllm.utils import direct_register_custom_op
|
|
|
|
global_counter = 0
|
|
|
|
# create a library to hold the custom op
|
|
silly_lib = Library("silly", "FRAGMENT") # noqa
|
|
|
|
|
|
def silly_attention(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor,
|
|
out: torch.Tensor) -> None:
|
|
global global_counter
|
|
global_counter += 1
|
|
print(f"{global_counter=}")
|
|
out.copy_(q)
|
|
out[0] += 1
|
|
|
|
|
|
def silly_attention_fake(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor,
|
|
out: torch.Tensor) -> None:
|
|
return
|
|
|
|
|
|
direct_register_custom_op(
|
|
op_name="attention",
|
|
op_func=silly_attention,
|
|
mutates_args=["out"],
|
|
fake_impl=silly_attention_fake,
|
|
target_lib=silly_lib,
|
|
)
|
|
|
|
|
|
@support_torch_compile
|
|
class SillyModel(nn.Module):
|
|
|
|
def __init__(self,
|
|
*,
|
|
vllm_config: VllmConfig,
|
|
prefix: str = '',
|
|
**kwargs) -> None:
|
|
super().__init__()
|
|
|
|
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
|
"""
|
|
Overall effect:
|
|
x += 1
|
|
x[0] += 2
|
|
global_counter += 2
|
|
"""
|
|
x = x + 1
|
|
x = x + 2
|
|
out = torch.empty_like(x)
|
|
torch.ops.silly.attention(x, x, x, out)
|
|
x = out
|
|
x = x - 2
|
|
x = x - 1
|
|
out = torch.empty_like(x)
|
|
torch.ops.silly.attention(x, x, x, out)
|
|
x = out
|
|
x = x + 1
|
|
return x
|
|
|
|
|
|
def test_simple_piecewise_compile():
|
|
|
|
vllm_config = VllmConfig(compilation_config=CompilationConfig(
|
|
level=CompilationLevel.PIECEWISE,
|
|
use_cudagraph=True,
|
|
splitting_ops=["silly.attention"],
|
|
cudagraph_copy_inputs=True,
|
|
cudagraph_capture_sizes=[1, 2],
|
|
))
|
|
with set_current_vllm_config(vllm_config):
|
|
model = SillyModel(vllm_config=vllm_config, prefix='')
|
|
|
|
inputs = torch.randn(100).cuda()
|
|
|
|
with compilation_counter.expect(
|
|
num_graphs_seen=1, # one graph for the model
|
|
num_piecewise_graphs_seen=5, # 2 * num_layers + 1
|
|
num_piecewise_capturable_graphs_seen=3, # 1 + num_layers
|
|
num_inductor_compilations=3, # num_piecewise_capturable_graphs_seen
|
|
num_cudagraph_caputured=
|
|
6, # num_cudagraph_sizes * num_piecewise_capturable_graphs_seen
|
|
):
|
|
|
|
model(inputs)
|
|
|
|
model(torch.randn(2).cuda())
|
|
model(torch.randn(1).cuda())
|
|
|
|
input = torch.zeros(2).cuda()
|
|
global global_counter
|
|
global_counter = 0
|
|
output = model(input)
|
|
assert global_counter == 2
|
|
assert torch.allclose(output.cpu(), torch.tensor([3., 1.]))
|