MoonshotAI / MoonshotAI/FlashKDA

gate mode diff

Open
#3 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
1.3k
Forks
122
PR merge metrics
No merged PRs in 30d

Description

Would you consider supporting softplus as an alternative activation mode (e.g., via a flag like gate_mode: "lower_bound" | "softplus")?
And, I tested fla's chunk_kda vs FlashKDA, in end to end result, lower_bound gate mode will cause repeatition in model's output.Both fla's chunk_kda with lower_bound gate mode and FlashKDA have the same problem, but when use fla's chunk_kda with softplus gate mode, it works fine.
the model used is kimi linear (https://modelscope.cn/models/moonshotai/Kimi-Linear-48B-A3B-Instruct).

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the chunk_kda and FlashKDA entry points and comparing how their gate modes are handled. Reproduce the reported repetition with Kimi Linear, then establish how softplus mode should be selected and verify that the end-to-end output no longer repeats.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.