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

Signed-off-by: Megha Agarwal <agarwalmegha1308@gmail.com>
Signed-off-by: meghaagr13 <divyanshsinghvi@gmail.com>
Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: meghaagr13 <divyanshsinghvi@gmail.com>
Co-authored-by: Boao Shi <aoibosh@connect.hku.hk>
Co-authored-by: Taichang Zhou <tzhouam@connect.ust.hk>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
authored and GitHub committed 2026-06-12 15:19:14 +08:00
1 parent 1be1a71156
commit 8f869c8ea5
49 files changed
+985 -327

No files matched your search

+4 -1
View File
@@ -117,7 +117,10 @@ class OmniEngineCoreRequest(EngineCoreRequest):
class OmniEngineCoreOutput(EngineCoreOutput):
pooling_output: dict[str, torch.Tensor] | None = None
# Dedicated channel for multimodal outputs (image/audio/latent).
# pooling_output is inherited from EngineCoreOutput as torch.Tensor | None
# and retains its original vLLM semantics for pooling/embedding tasks.
multimodal_output: dict[str, torch.Tensor] | None = None
# Finished flag for streaming input segment
is_segment_finished: bool | None = False
# Streaming update prompt length