This website requires JavaScript.
Explore
Help
Sign In
anodyine
/
vllm-omni
Watch
1
Star
0
Fork
0
Code
Issues
4
Pull Requests
2
Actions
Packages
Projects
Releases
Wiki
Activity
Files
eeee25791327d94bd5ea5460f5df7c1f7198d4e8
vllm-omni
/
vllm_omni
/
diffusion
/
attention
T
History
Xenoryn
and
Claude
039808e0d9
[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (
#5717
)
...
Signed-off-by: Xenoryn <
timberh2000@outlook.com
> Co-authored-by: Claude <
noreply@anthropic.com
>
2026-09-06 16:23:30 +08:00
..
backends
[Model] Add native MAGI-2 Preview diffusion support (
#5918
)
2026-09-05 15:32:30 +08:00
ops
[Bugfix] Preserve BF16 residual semantics in fused MiniMax-H3 modulation (
#6878
)
2026-09-04 02:01:34 +08:00
parallel
[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (
#5717
)
2026-09-06 16:23:30 +08:00
__init__.py
[Diffusion] Init Attention Backends and Selector for Diffusion (
#115
)
2025-12-05 10:46:20 +00:00
layer.py
[Model] Add native MAGI-2 Preview diffusion support (
#5918
)
2026-09-05 15:32:30 +08:00
selector.py
[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (
#5543
)
2026-09-02 15:39:49 +00:00