Logo
Explore Help
Sign In
DeepSeek/FlashMLA
1
0
Fork 0
You've already forked FlashMLA
mirror of https://github.com/deepseek-ai/FlashMLA synced 2025-06-26 18:15:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
Files
e0557deb3a4ea436f166cd84a7b85727b2f7eb85
FlashMLA/csrc
History
Kevin Zhang e0557deb3a Feature:Support flashMLA decoding via flashAttn2(#29)
Changes:
1. Implement flashMLA with matrix absorption algorithm via flashAttn2
2. Add golden test on MXMACA platform
2025-02-24 23:56:05 +08:00
..
flash_api_mla.cpp
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_api_mla.h
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_api.cpp
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_fwd_mla_kernel.h
Initial commit
2025-02-24 09:20:23 +08:00
flash_fwd_split_kernel_k64_V1x8.h
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_fwd_splitkv_hdimqk576_hdimv512_m32n16_bf16_True_True_sm80.cu
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_fwd_splitkv_hdimqk576_hdimv512_m32n16_bf16_True_True_split_sm80.cu
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_fwd_splitkv_hdimqk576_hdimv512_m32n16_fp16_True_True_sm80.cu
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_fwd_splitkv_hdimqk576_hdimv512_m32n16_fp16_True_True_split_sm80.cu
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
flash_parameter.h
Feature:Support flashMLA decoding via flashAttn2(#29)
2025-02-24 23:56:05 +08:00
Powered by Gitea Version: 1.25.4 Page: 20ms Template: 4ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API