[WIP]Add Ascend NPU fallbacks for core ops#182
Open
bitdousi wants to merge 3 commits intodatabricks:mainfrom
Open
[WIP]Add Ascend NPU fallbacks for core ops#182bitdousi wants to merge 3 commits intodatabricks:mainfrom
bitdousi wants to merge 3 commits intodatabricks:mainfrom
Conversation
Provide pure-PyTorch implementations for histogram/cumsum/replicate/sort/topology when tensors are on NPU, while keeping the existing CUDA extension path for CUDA tensors. Made-with: Cursor
bitdousi
changed the title
added 2 commits
March 9, 2026 15:48
Route gather/scatter/padded and binned kernels to a pure-PyTorch backend on Ascend NPU (or when Triton isn't available), while keeping existing Triton implementations for CUDA. Made-with: Cursor
Add Python implementations for cumsum/histogram/sort/indices/replicate under megablocks.backend.npu_ops to support Ascend NPU without shadowing the upstream megablocks_ops C++ extension. Made-with: Cursor
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Provide pure-PyTorch implementations for histogram/cumsum/replicate/sort/topology when tensors are on NPU, while keeping the existing CUDA extension path for CUDA tensors.
Made-with: Cursor
What does this PR do?
What issue(s) does this change relate to?
Before submitting
pre-commiton your change? (see thepre-commitsection of prerequisites)