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

..

assets

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

config

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

core

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

diffusion

[diffusion] use fa3 by default when device supports it (#783)

2026-01-22 15:00:29 +08:00

distributed

[Feature]Basic version of supporting streaming output (#367)

2026-01-01 03:02:04 +13:00

engine

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

entrypoints

[bugfix] support text + audio mixed output (#843)

2026-01-21 17:44:17 +08:00

inputs

[Rebase] Rebase to vllm 0.12.0 (#335)

2025-12-19 16:42:02 +08:00

model_executor

[Perf] Fuse Q/K/V Linear with QKVParallelLinear in Qwen2.5Omni DiTAttention (#884)

2026-01-21 09:24:05 +00:00

sample

update dirs

2025-09-11 15:43:43 +08:00

utils

[Core]Add GPU Diffusion Runner (#822)

2026-01-17 19:49:13 +08:00

worker

Dev/rebase 0.14.0 (#847)

2026-01-21 00:25:25 +08:00

__init__.py

[Feat] Rename AsyncOmniLLM -> AsyncOmni (#103)

2025-11-30 22:26:33 +08:00

logger.py

[BugFix] Failed to print DEBUG level log (#307)

2025-12-15 07:13:36 +00:00

outputs.py

[Core] Supports stage abstraction in the diffusion model (#391)

2025-12-27 01:59:33 +13:00

patch.py

[NPU][Upgrade] Upgrade to v0.12.0 (#447)

2025-12-26 14:10:23 +08:00

request.py

[Rebase] Rebase to vllm 0.12.0 (#335)

2025-12-19 16:42:02 +08:00

version.py

Bump version to 0.12.0rc1 (#399)

2025-12-22 15:00:13 +08:00