deepseek-ai / deepseek-ai/FlashMLA

[Bug] Sequence length = 0

Open
#11 1 comment 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

Hi! Probably not a common case, but the kernel doesn't seem to support sequence_lengths = 0 natively. I can try to make a patch, but could you help provide some pointers? Thanks!

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are identified in the issue. Begin by locating the FlashMLA kernel path that consumes sequence_lengths and reproduce the sequence_lengths = 0 case. Done means the kernel handles zero-length sequences correctly, with regression coverage for this input.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.