vllm-omni

anodyine/vllm-omni

0 Fork 0

Files

T

History

504698dec8 [Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527 )

Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>

2026-06-29 17:43:36 +02:00

__init__.py

[Core] Support Async & Sync AutoRegressive Scheduling (#3306 )

2026-05-05 12:09:45 +08:00

omni_ar_scheduler.py

[Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527 )

2026-06-29 17:43:36 +02:00

omni_generation_scheduler.py

[Refactor] Output Processor Phase 2: separate multimodal output channel (#1601 ) (#2744 )

2026-06-12 15:19:14 +08:00

omni_scheduler_mixin.py

[Bugfix] purge chunk-transfer zombies on every schedule tick to keep engine-core alive on aborts (fixes #3736 ) (#3774 )