This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
f8a08cb90dc0b5b45663cd2605d0c98c77efe009
vLLM
/
vllm
/
attention
T
History
Travis Johnson
0032903a5b
[Bugfix] detect alibi and revert to FA2 (
#15231
)
...
Signed-off-by: Travis Johnson <
tsjohnso@us.ibm.com
>
2025-03-20 19:20:16 -07:00
..
backends
[Bugfix] detect alibi and revert to FA2 (
#15231
)
2025-03-20 19:20:16 -07:00
ops
[Kernel] [V1] Further optimizations to ROCm (Triton) Backend to better handle GQA. (
#14431
)
2025-03-13 20:42:27 -07:00
__init__.py
[Attention] Flash Attention 3 - fp8 (
#14570
)
2025-03-20 01:14:20 -04:00
layer.py
[Attention] Flash Attention 3 - fp8 (
#14570
)
2025-03-20 01:14:20 -04:00
selector.py
Correct capitalisation:
VLLM
->
vLLM
(
#14562
)
2025-03-10 16:36:21 +00:00