是否支持流式音频输入 audio_encoder 推理,这样LLM也可以进行流式prefill #36

Open

opened

on Dec 24, 2025

目前跟进去看 masks是全量的mask

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests