Logo
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
28a6597c4ccfb39c60ce675f0c0da367ef7904f8
vllm-omni/vllm_omni/diffusion/attention/backends
T
History
Jiangyun Zhu 0df8e80574 [diffusion] use fa3 by default when device supports it (#783)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
2026-01-22 15:00:29 +08:00
..
ring
[Diffusion]: Diffusion Ring Attention support (#273)
2025-12-31 14:26:30 +00:00
utils
[Feature] Flash Attention to Support Attention Mask (#760)
2026-01-16 11:01:11 +08:00
__init__.py
[Diffusion] Init Attention Backends and Selector for Diffusion (#115)
2025-12-05 10:46:20 +00:00
abstract.py
[Bugfix] Solve Ulysses-SP sequence length not divisible by SP degree (using padding and attention mask) (#672)
2026-01-08 00:02:22 +08:00
ascend_attn.py
[Model] Support Qwen-Image series models on NPU (#463)
2025-12-27 10:46:10 +08:00
flash_attn.py
[diffusion] use fa3 by default when device supports it (#783)
2026-01-22 15:00:29 +08:00
ring_flash_attn.py
[Bugfix] Raise ValueError when joint_strategy='rear' and causal=True in Ring Attention (#767)
2026-01-13 17:13:31 +08:00
ring_pytorch_attn.py
[Bugfix] Raise ValueError when joint_strategy='rear' and causal=True in Ring Attention (#767)
2026-01-13 17:13:31 +08:00
sage_attn.py
[Diffusion][Attention] sage attention backend (#243)
2025-12-13 08:17:41 +08:00
sdpa.py
[Diffusion] Init Attention Backends and Selector for Diffusion (#115)
2025-12-05 10:46:20 +00:00
Powered by Gitea Version: 28.1.0 Page: 45ms Template: 2ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API