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
52c8f8dbc8db824c45ddf4360b7b80cc20bac813
vllm-omni
/
vllm_omni
/
diffusion
/
layers
/
mot
T
History
hsliuustc0106
52c8f8dbc8
Support one-sided MoT biases
...
Signed-off-by: hsliuustc0106 <
liuhongsheng4@huawei.com
>
2026-09-03 17:05:57 +00:00
..
ops
Support one-sided MoT biases
2026-09-03 17:05:57 +00:00
__init__.py
[Enhancement] Introduce High-Performance MoT (Mixture-of-Tokens) Kernels: Triton Implementation (
#3960
)
2026-06-16 03:08:02 +00:00
mot_layernorm.py
[Enhancement] Introduce High-Performance MoT (Mixture-of-Tokens) Kernels: Triton Implementation (
#3960
)
2026-06-16 03:08:02 +00:00
mot_qkv_parallel_linear.py
[Rebase] Rebase to vllm 0.28.0 (
#6606
)
2026-08-27 06:12:55 +00:00
mot_row_parallel_linear.py
[Rebase] Rebase to vllm 0.28.0 (
#6606
)
2026-08-27 06:12:55 +00:00