This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
1fd471e957526a34a0cb4b60d2e830cd6ca79fdc
vLLM
/
vllm
/
attention
T
History
Cyrus Leung
9fb52e523a
[V1] Support any head size for FlexAttention backend (
#20467
)
...
Signed-off-by: DarkLight1337 <
tlleungac@connect.ust.hk
>
2025-07-06 09:54:36 -07:00
..
backends
[V0 deprecation] Remove V0 CPU/XPU/TPU backends (
#20412
)
2025-07-06 08:48:13 -07:00
ops
[TPU] kv cache update kernel supports dynamic grid (
#20235
)
2025-07-02 06:33:37 +00:00
utils
Quick Fix by adding conditional import for flash_attn_varlen_func in flash_attn (
#20143
)
2025-06-27 05:48:13 +00:00
__init__.py
[Misc] Add SPDX-FileCopyrightText (
#19100
)
2025-06-03 11:20:17 -07:00
layer.py
[V1] Support any head size for FlexAttention backend (
#20467
)
2025-07-06 09:54:36 -07:00
selector.py
[V1] Support any head size for FlexAttention backend (
#20467
)
2025-07-06 09:54:36 -07:00