Public
sparse
6 items
..
Go back to parent directory
instantiations
Jan 23, 2026
FOLDER
Last modified by WebDev
config.h
4.22 KB
Jan 23, 2026
H
Last modified by WebDev
fwd.cu
851 B
Jan 23, 2026
CU
Last modified by WebDev
fwd.h
112 B
Jan 23, 2026
H
Last modified by WebDev
phase1.cuh
26.76 KB
Jan 23, 2026
CUH
Last modified by WebDev
phase1.h
175 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
134 views
Updated Jan 23, 2026
Languages
C++
60.1%
C
20.3%
Python
19.5%
LICENSE
0.2%