[Bugfix] Fix Deepseek V4 import error due to AOT compile cache loading (#41090)

Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
This commit is contained in:
Wei Zhao
2026-04-28 21:08:16 -07:00
committed by GitHub
parent 1312f07531
commit 803b9d7881
+5 -5
View File
@@ -1097,6 +1097,11 @@ class DeepseekV4DecoderLayer(nn.Module):
aux_stream_list: list[torch.cuda.Stream] | None = None,
):
super().__init__()
# Lazy import to avoid top-level tilelang dependency.
# Registers both torch.ops.vllm.mhc_pre and mhc_post
import vllm.model_executor.layers.mhc # noqa: F401
config = vllm_config.model_config.hf_config
self.hidden_size = config.hidden_size
@@ -1167,11 +1172,6 @@ class DeepseekV4DecoderLayer(nn.Module):
hc_scale: torch.Tensor,
hc_base: torch.Tensor,
):
# Lazy import to avoid top-level tilelang dependency.
# Registers both torch.ops.vllm.mhc_pre and mhc_post,
# so hc_post() doesn't need its own import.
import vllm.model_executor.layers.mhc # noqa: F401
post_mix, res_mix, layer_input = torch.ops.vllm.mhc_pre(
residual=x,
fn=hc_fn,