Skip to content
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

[CI/Build][CPU][Bugfix] Fix CPU CI #12150

Merged
merged 1 commit into from
Jan 17, 2025
Merged

[CI/Build][CPU][Bugfix] Fix CPU CI #12150

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions .buildkite/run-cpu-test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,6 @@ function cpu_tests() {
tests/lora/test_qwen2vl.py"
}

# All of CPU tests are expected to be finished less than 25 mins.
# All of CPU tests are expected to be finished less than 40 mins.
export -f cpu_tests
timeout 30m bash -c "cpu_tests $CORE_RANGE $NUMA_NODE"
timeout 40m bash -c "cpu_tests $CORE_RANGE $NUMA_NODE"
8 changes: 6 additions & 2 deletions vllm/model_executor/layers/activation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,10 @@ class FatreluAndMul(CustomOp):
def __init__(self, threshold: float = 0.):
super().__init__()
self.threshold = threshold
if current_platform.is_cuda_alike() or current_platform.is_cpu():
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggested:

if current_platform.is_cpu():
    self._forward_method = self.forward_native

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated

if current_platform.is_cuda_alike():
self.op = torch.ops._C.fatrelu_and_mul
elif current_platform.is_cpu():
self._forward_method = self.forward_native

def forward_native(self, x: torch.Tensor) -> torch.Tensor:
d = x.shape[-1] // 2
Expand Down Expand Up @@ -100,11 +102,13 @@ class MulAndSilu(CustomOp):

def __init__(self):
super().__init__()
if current_platform.is_cuda_alike() or current_platform.is_cpu():
if current_platform.is_cuda_alike():
self.op = torch.ops._C.mul_and_silu
elif current_platform.is_xpu():
from vllm._ipex_ops import ipex_ops
self.op = ipex_ops.silu_and_mul
elif current_platform.is_cpu():
self._forward_method = self.forward_native

def forward_native(self, x: torch.Tensor) -> torch.Tensor:
"""PyTorch-native implementation equivalent to forward()."""
Expand Down
Loading