vllm-omni/vllm_omni/diffusion/attention at 8f45e68bcd4b5beb44c45ddbb576e59ea9c7a741 - vllm-omni - Gitea: Git with a cup of tea

anodyine/vllm-omni

0 Fork 0

Files

T

History

Lancer 109bba8cdf [Bugfix] Treat kv_cache_dtype=auto as unset for ring attention (#3622 )

Signed-off-by: Lancer <maruixiang6688@gmail.com>

2026-05-20 05:18:57 +00:00

..

[XPU] set flash_attn as default diffusion attn backend and fix k_len for cross_attn (#3525 )

2026-05-18 23:58:15 +00:00

[Diffusion][Attention] Support per-role attention backend via CLI (#2681 )

2026-05-10 11:59:05 +08:00

__init__.py

[Diffusion] Init Attention Backends and Selector for Diffusion (#115 )

2025-12-05 10:46:20 +00:00

layer.py

[Bugfix] Treat kv_cache_dtype=auto as unset for ring attention (#3622 )

2026-05-20 05:18:57 +00:00

selector.py

[Diffusion][Attention] Support per-role attention backend via CLI (#2681 )

2026-05-10 11:59:05 +08:00