mirror of
https://github.com/deepseek-ai/DeepSeek-V3.git
synced 2026-11-05 00:47:48 +00:00
[GH-ISSUE #18] Any comparison of MLA vs MQA? #13
Labels
No labels
closed-as-stale
enhancement
question
spam
stale
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-V3#13
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @chaoyan1037 on GitHub (Dec 28, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V3/issues/18
The V2 paper only directly compared MLA with MHA. Table 8 in V2 paper only compares dense models with MHA, MQA, and GQA, without MLA. Table 9 compares MoE models with MHA and MLA, without MQA or GQA.
I feel the MLA is kind of similar to MQA in the essence. I am curious if there are any apple-to-apple ablation studies on MLA vs MQA?
@MonolithFoundation commented on GitHub (Jan 9, 2025):
MLA didn't have obvious performance enhance compare with MQA, however, not worse either, but faster.
@github-actions[bot] commented on GitHub (Feb 9, 2025):
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!
@github-actions[bot] commented on GitHub (Feb 25, 2025):
false