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
348fd0fc07258a02732b07c7f32a9f3ba3b56ff9
vllm-omni
/
vllm_omni
/
diffusion
/
attention
T
History
Bo Li
fda3af8bbc
[Bugfix] Preserve BF16 residual semantics in fused MiniMax-H3 modulation (
#6878
)
...
Signed-off-by: Bo Li <
22713281+bobboli@users.noreply.github.com
>
2026-09-04 02:01:34 +08:00
..
backends
[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (
#5543
)
2026-09-02 15:39:49 +00:00
ops
[Bugfix] Preserve BF16 residual semantics in fused MiniMax-H3 modulation (
#6878
)
2026-09-04 02:01:34 +08:00
parallel
[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (
#5543
)
2026-09-02 15:39:49 +00:00
__init__.py
[Diffusion] Init Attention Backends and Selector for Diffusion (
#115
)
2025-12-05 10:46:20 +00:00
layer.py
[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (
#5543
)
2026-09-02 15:39:49 +00:00
selector.py
[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (
#5543
)
2026-09-02 15:39:49 +00:00
