deepseek-ai / deepseek-ai/FlashMLA

consult questions about lower kv_lora_rank support

Open
#78 0 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

I wonder if FlashMLA supports MLA with parameters other than d(head_dim_q)=576 ?
For example, if I can test FlashMLA with head_dim_qk = 256 + 64 and head_dim_vo = 256 with just a small code change?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.