microsoft / microsoft/MInference

[Question]: quick evaluation of kernel

Open
#180 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Describe the issue

This code is to evaluate three sparse attention func separately, is there a quick way to evaluate the time cost of MInference?

attn_output = vertical_slash_sparse_attention(q, k, v, vertical_topk, slash)
attn_output = block_sparse_attention(q, k, v, topk)
attn_output = streaming_forward(q, k, v, init_num, local_window_num)

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 from the three listed entry points: vertical_slash_sparse_attention, block_sparse_attention, and streaming_forward. Run them with representative q, k, v and their shown parameters, then compare measured execution times; the work is done when a reproducible timing approach and results for the three functions are available.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.