biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-09-06 16:15:18 -07:00
committed by GitHub
parent 848562bd49
commit 4172235ab7
46 changed files with 10 additions and 5462 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/model_executor/custom_op.py
View File

@@ -73,11 +73,6 @@ class CustomOp(nn.Module):
# NOTE(woosuk): This is a placeholder for future extensions.
return self.forward_native(*args, **kwargs)
def forward_neuron(self, *args, **kwargs):
# By default, we assume that Neuron ops are compatible with the
# PyTorch-native implementation.
return self.forward_native(*args, **kwargs)
def forward_oot(self, *args, **kwargs):
# By default, we assume that OOT ops are compatible with the
# PyTorch-native implementation.
@@ -105,8 +100,6 @@ class CustomOp(nn.Module):
return self.forward_tpu
elif current_platform.is_xpu():
return self.forward_xpu
elif current_platform.is_neuron():
return self.forward_neuron
elif current_platform.is_out_of_tree():
return self.forward_oot
else: