[Refactor/Bugfix] Use Delta Messages for Streaming (#2911)

Signed-off-by: Alex Brooks <albrooks@redhat.com>
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Sy03 <1370724210@qq.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-04-26 15:11:53 +12:00
1 parent 6e35bfbbae
commit e03ab82dd2
27 files changed
+623 -177

No files matched your search

@@ -13,7 +13,7 @@ def _source_output(request_id: str, prompt_ids: list[int], out_ids: list[int], m
return SimpleNamespace(
request_id=request_id,
prompt_token_ids=prompt_ids,
outputs=[SimpleNamespace(token_ids=out_ids, multimodal_output=mm)],
outputs=[SimpleNamespace(token_ids=out_ids, cumulative_token_ids=out_ids, multimodal_output=mm)],
)
@@ -27,7 +27,7 @@ pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
def _source_output(token_ids: list[int], mm_output: dict | None = None):
"""Create a minimal AR output mock."""
return SimpleNamespace(
outputs=[SimpleNamespace(token_ids=token_ids)],
outputs=[SimpleNamespace(token_ids=token_ids, cumulative_token_ids=token_ids)],
multimodal_output=mm_output,
)
@@ -336,6 +336,7 @@ def test_non_async_processor_prepends_ref_code_and_sets_trim_context():
output = SimpleNamespace(
multimodal_output={"codes": {"audio": audio_codes, "ref": ref_code}},
token_ids=list(range(3)),
cumulative_token_ids=list(range(3)),
)
stage = SimpleNamespace(
engine_outputs=[SimpleNamespace(outputs=[output], finished=True)],
@@ -381,6 +382,7 @@ def test_non_async_processor_filters_out_of_range_codec_values():
output = SimpleNamespace(
multimodal_output={"codes": {"audio": audio_codes, "ref": ref_code}},
token_ids=list(range(4)),
cumulative_token_ids=list(range(4)),
)
stage = SimpleNamespace(
engine_outputs=[SimpleNamespace(outputs=[output], finished=True)],