microsoft / microsoft/MInference

[Question]: Why are the sparse patterns in the provided configuration files all “vertical_and_slash”?

Open
#120 4 comments 0 reactions 1 assignee View on GitHub

@iofu728 is already working on this.

Since Feb 12, 2025.

question
Dominant language
Python
Stars
1.2k
Forks
82
Avg merge
1d 18h
Merged PRs (30d)
1

Description

Describe the issue

Hi, thanks for the great work!

I am curious about the provided configuration files. In my understanding, these files are used to determine the attention pattern of an attention head. However, I find the attention patterns are always the vertical_and_slash pattern (e.g. Llama_3_8B_Instruct_262k_kv_out_v32_fit_o_best_pattern.json). Does this mean that there is no need to divide sparse patterns into three types?

Thanks!

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.