[main][bugfix] Unify MoE routing init with standard torch_npu operator #2401
+13
−39
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR fixes the dependency on a POC version of
torch_npu
for the MoE routing initialization feature.Before:
To get the best performance, users needed a
torch_npu
version containing thenpu_moe_init_routing_quant
operator. Official versions would trigger a slower, pure PyTorch fallback.After:
The code is updated to use the
npu_moe_init_routing_v2
operator, which is included in the officialtorch_npu
releases and provides equivalent performance. This change unifies the implementation, removes the fallback logic, and makes the high-performance path accessible to all users without requiring a special library version.