Conversation
PR #25810 introduced the model-level MHC token-count prewarm call chain. PR #26238 removed all callers by routing MHC prenorm through the unified DeepGEMM wrapper warmup infrastructure. PR #25976 then re-added the definition in DeepseekV4DecoderLayer without restoring any caller, leaving it as dead code. Remove it.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
The only caller was prewarm_mhc_token_count_buckets which was removed in the previous commit.
41 tasks
Jiminator
deleted the
fix/remove-dead-prewarm-mhc-token-count-buckets
branch
September 14, 2026 04:42
alexnails
restored the
fix/remove-dead-prewarm-mhc-token-count-buckets
branch
September 14, 2026 05:44
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
DeepseekV4DecoderLayer.prewarm_mhc_token_count_bucketsandprewarm_mhc_token_countsare dead code with no callers.Timeline:
DeepseekV4DecoderLayerwithout restoring any caller, leaving them as dead code.This happened because #25976 was developed in parallel with #26238. When #25976 was merged after #26238, it re-introduced the function definitions based on the older code, but the callers that #26238 had already removed were not restored — resulting in orphaned dead code.
Modifications
Remove
prewarm_mhc_token_count_bucketsandprewarm_mhc_token_countsfromDeepseekV4DecoderLayer(116 lines).cc @YAMY1234 @Fridge003 @JoeLee314 @ch-wan
CI States
Latest PR Test (Base): ❌ Run #26686294856
Latest PR Test (Extra): ❌ Run #26686294831
Latest PR Test (AMD ROCm 10): ➖ No AMD PR run found for this commit.