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:
49 files changed
+985
-327
No files matched your search
@@ -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
|
||||
|
||||
Reference in new issue
Block a user