- 08 Jul, 2024 7 commits
-
-
Simon Mo authored
-
tomeras91 authored
-
Eric authored
-
afeldman-nm authored
[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) (#4888) Co-authored-by:Woosuk Kwon <woosuk.kwon@berkeley.edu>
-
Avshalom Manevich authored
-
Haichuan authored
Co-authored-by:Roger Wang <ywang@roblox.com>
-
kczimm authored
-
- 07 Jul, 2024 4 commits
-
-
youkaichao authored
Co-authored-by:Cody Yu <hao.yu.cody@gmail.com>
-
Robert Shaw authored
Co-authored-by:Robert Shaw <rshaw@neuralmagic>
-
Haichuan authored
Co-authored-by: -
Roger Wang authored
Co-authored-by:
-
- 06 Jul, 2024 3 commits
-
-
Cyrus Leung authored
-
Roger Wang authored
-
Simon Mo authored
-
- 05 Jul, 2024 9 commits
-
-
Simon Mo authored
-
Simon Mo authored
-
Simon Mo authored
-
Simon Mo authored
-
JGSweets authored
-
jvlunteren authored
-
Christian Rohmann authored
Signed-off-by:Christian Rohmann <christian.rohmann@inovex.de>
-
Cyrus Leung authored
-
Roger Wang authored
-
- 04 Jul, 2024 7 commits
-
-
Cyrus Leung authored
-
Lily Liu authored
Co-authored-by:Simon Mo <simon.mo@hey.com>
-
Yuan authored
Signed-off-by:Yuan Zhou <yuan.zhou@intel.com>
-
youkaichao authored
-
Gregory Shtrasberg authored
[ROCm][AMD][Model]Adding alibi slopes support in ROCm triton flash attention and naive flash attention (#6043) Co-authored-by:Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
-
Cyrus Leung authored
-
Murali Andoorveedu authored
Signed-off-by:Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
-
- 03 Jul, 2024 10 commits
-
-
Travis Johnson authored
Signed-off-by:
Travis Johnson <tsjohnso@us.ibm.com> Co-authored-by:
Nick Hill <nickhill@us.ibm.com>
-
youkaichao authored
-
youkaichao authored
-
Robert Shaw authored
-
xwjiang2010 authored
Signed-off-by:
Xiaowei Jiang <xwjiang2010@gmail.com> Co-authored-by:
-
youkaichao authored
-
Michael Goin authored
-
Roger Wang authored
-
Roger Wang authored
-
Roger Wang authored
Co-authored-by:Cyrus Leung <cyrus.tl.leung@gmail.com>
-
