diff options
author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-05-18 17:12:56 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-05-18 17:12:56 +0200 |
commit | eefc1c77ef00b74e1f8c6ac4e217dfbdbd419eff (patch) | |
tree | f0b827599e5c6746258b275fc593d16d86427de9 /candle-flash-attn | |
parent | 01545f73038cb8c90426214ddf4bcedd59e291e8 (diff) | |
download | candle-eefc1c77ef00b74e1f8c6ac4e217dfbdbd419eff.tar.gz candle-eefc1c77ef00b74e1f8c6ac4e217dfbdbd419eff.tar.bz2 candle-eefc1c77ef00b74e1f8c6ac4e217dfbdbd419eff.zip |
Support flash-attn in quantized phi3. (#2194)
Diffstat (limited to 'candle-flash-attn')
0 files changed, 0 insertions, 0 deletions