squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[XPU] fallback to native implementation for xpu custom op (#7670)

Browse Source
This commit is contained in:
jianyizh 2024-08-20 15:26:09 +08:00 committed by GitHub
parent c4be16e1a7
commit e6d811dd13
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/custom_op.py
View File

@ -30,7 +30,9 @@ class CustomOp(nn.Module):
return self.forward_cuda(*args, **kwargs)
def forward_xpu(self, *args, **kwargs):
raise NotImplementedError
# By default, we assume that XPU ops are compatible with the
# PyTorch-native implementation.
return self.forward_native(*args, **kwargs)
def forward_cpu(self, *args, **kwargs):
# By default, we assume that CPU ops are compatible with CUDA ops.