Public
sparse_fp8
5 items
..
Go back to parent directory
components
Jan 23, 2026
FOLDER
Last modified by WebDev
instantiations
Jan 23, 2026
FOLDER
Last modified by WebDev
config.h
9.07 KB
Jan 23, 2026
H
Last modified by WebDev
splitkv_mla.cuh
38.44 KB
Jan 23, 2026
CUH
Last modified by WebDev
splitkv_mla.h
207 B
Jan 23, 2026
H
Last modified by WebDev
About
FlashMLA is a collection of highly optimized attention kernels (核心代码模块) developed by DeepSeek-AI. It's not a user-facing app, but rather a foundational library used to power their large language models like DeepSeek-V3 and DeepSeek-V3.2-Exp.
130 files
53 folders
1.13 MB total size
0 open issues
0 open pull requests
0 watchers
0 forks
0 stars
157 views
Updated Jan 23, 2026
Languages
C++
60.1%
C
20.3%
Python
19.5%
LICENSE
0.2%