Skip to content

[Bugfix] Fix Qwen2.5-Omni-7B accuarcy test #4556

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

Merged
wangxiyuan merged 1 commit into from
Dec 2, 2025
Merged

[Bugfix] Fix Qwen2.5-Omni-7B accuarcy test #4556

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
6 changes: 3 additions & 3 deletions vllm_ascend/ops/layernorm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,13 +108,13 @@ def forward_oot(
residual: Optional[torch.Tensor] = None,
) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
import torch_npu

if residual is not None:
residual = torch.ops.vllm.maybe_chunk_residual(x, residual)
assert x.size(0) == residual.size(0)
next_need_quant_fusion_linear = getattr(
self, 'next_need_quant_fusion_linear', None)
x, residual = _addrmsnorm_forward_oot(
self, x, residual, self.next_need_quant_fusion_linear,
self.bias)
self, x, residual, next_need_quant_fusion_linear, self.bias)
return x, residual
x, residual = torch_npu.npu_rms_norm(x, self.weight,
self.variance_epsilon)
Expand Down
8 changes: 6 additions & 2 deletions vllm_ascend/ops/register_custom_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,9 @@ def _maybe_prefetch_mlp_down_proj_impl(x_dependency: torch.Tensor) -> None:
except AssertionError:
return

if not forward_context.prefetch_mlp_enabled:
prefetch_mlp_enabled = getattr(forward_context, 'prefetch_mlp_enabled',
False)
if not prefetch_mlp_enabled:
return
forward_context.prefetch_mlp_down_proj = True
model_instance = forward_context.model_instance
Expand Down Expand Up @@ -202,7 +204,9 @@ def _maybe_wait_prefetch_done_impl(x: torch.Tensor) -> None:
except AssertionError:
return

if not forward_context.prefetch_mlp_enabled:
prefetch_mlp_enabled = getattr(forward_context, 'prefetch_mlp_enabled',
False)
if not prefetch_mlp_enabled:
return
if forward_context.prefetch_mlp_gate_up_proj or \
forward_context.prefetch_mlp_down_proj:
Expand Down
Loading