Conversation
Implement token alignment operator on Metax backend for Mixture-of-Experts. Given top-k expert assignments (topk_ids), sorts tokens by expert index, computes per-expert token counts with block-size aligned padding, and produces sorted_token_ids, expert_ids, and num_tokens_post_padded for downstream grouped GEMM dispatch. Supports optional expert_map for expert remapping.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implement token alignment operator on Metax backend for Mixture-of-Experts.
Given top-k expert assignments (topk_ids), sorts tokens by expert index,
computes per-expert token counts with block-size aligned padding, and
produces sorted_token_ids, expert_ids, and num_tokens_post_padded for
downstream grouped GEMM dispatch. Supports optional expert_map for
expert remapping.
编译core
单元测试
模型验证：
python examples/test_infer.py --device metax --model=/data/rubik/models/Qwen3-30B-A3B-Instruct-2507/ --enable-paged-attn --tp 2 --disable-prefix-caching --prompt "who are you"