deepseek-ai / deepseek-ai/FlashMLA

q的sequence length也是任意的吗?还是只是支持小数字的?

Open
#28 6 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
12.9k
Forks
1.2k
Avg merge
4h 20m
Merged PRs (30d)
2

Description

看了看代码,是双阶段flash decode形式的mla, python测试代码中s_q为1或2,s_q能支持任意长度?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the Python test code, especially the cases where s_q is 1 or 2, and trace the corresponding MLA FlashMLA decode entry point. Confirm the supported q sequence-length range from the implementation or tests, then document whether arbitrary lengths are supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.