feat: implement CPT-MoE Router v1 from the frozen specification - #1
Open
wwd43 wants to merge 2 commits into
Open
feat: implement CPT-MoE Router v1 from the frozen specification#1wwd43 wants to merge 2 commits into
wwd43 wants to merge 2 commits into
Conversation
mikecovlee
requested changes
Aug 1, 2026
| ) | ||
| # padding: [B, 1, 1, S] → 控制哪些 key 可见 | ||
| combined = combined & attention_mask[:, None, None, :] | ||
| if segment_ids is not None: |
Owner
There was a problem hiding this comment.
为什么这里需要在Attention里面注入segment_ids
| pad_4d = attention_mask[:, None, None, :] # [B, 1, 1, S] | ||
| combined = causal[None, None, :, :] & pad_4d # [B, 1, S, S] | ||
| combined = causal[None, None, :, :] | ||
| if attention_mask is not None: |
Owner
There was a problem hiding this comment.
代码风格不一致，有的用nn.Parameters, 有的用register，考虑统一
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Validation
No formal long-training, quality, specialization, or throughput claims are made.