anodyine/vllm-omni

0 Fork 0

Files

T

History

a7ab91fb85 [Example] Migrate HunyuanImage-3.0 to model_extras + shared task examples (#5559 )

Signed-off-by: suyanli220 <suyanli220@gmail.com>
Signed-off-by: suyan.li <suyan.li@bytedance.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: suyan.li <suyan.li@bytedance.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-09-11 16:47:25 +08:00

cli

[Perf][Diffusion] Optimize HSDP startup via Rank-0 shared weight loading and accelerated LoRA delta computation (#7005 )

2026-09-11 08:28:42 +00:00

duplex

[Realtime] Emit current (non-beta) OpenAI audio/transcript event names (#7339 )

2026-09-11 08:50:12 +08:00

openai

[Example] Migrate HunyuanImage-3.0 to model_extras + shared task examples (#5559 )

2026-09-11 16:47:25 +08:00

openpi

Cosmos3 action policy improvements (#6460 )

2026-09-10 22:32:50 +08:00

serve

[Refactor] P0.2: Migrate API server helpers out of api_server (#5453 )

2026-09-10 15:03:21 +08:00

__init__.py

[Bug] Lazy-import entrypoints to fix subprocess pynvml crash (#2187 )

2026-04-09 15:35:22 +08:00

async_omni.py

[Rebase] Rebase to vLLM 0.29.0 (#7230 )

2026-09-10 12:08:28 +08:00

client_request_state.py

[Bugfix] Fix host-memory leak on aborted /v1/images/generations (#6462 ) (#6561 )

2026-09-11 00:04:08 +00:00

duplex_request_client.py

[Core] Graduate MiniCPM-o 4.5 and PersonaPlex full-duplex serving out of experimental (#6196 )

2026-09-05 08:20:21 +00:00

omni_base.py

[Bugfix] Fix host-memory leak on aborted /v1/images/generations (#6462 ) (#6561 )

2026-09-11 00:04:08 +00:00

omni.py

text and image metric (#6150 )

2026-08-26 02:54:45 +00:00

pd_utils.py

[Bugfix] Remove stale OmniStage import and type annotation (#3541 )

2026-05-22 11:32:14 +08:00

README.md

[Refactor] P0.2: Migrate API server helpers out of api_server (#5453 )

2026-09-10 15:03:21 +08:00

stage_utils.py

[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367 )

2026-08-29 09:11:39 +00:00

utils.py

[Model] Optimize MOSS-TTS Local batched execution and streaming codec (#7202 )

2026-09-09 13:02:12 -07:00

README.md

Entrypoints

This package contains user-facing server, CLI, orchestration, and protocol entrypoints for vLLM-Omni.

What Belongs Here

Runtime orchestration entrypoints such as AsyncOmni, Omni, and request-state helpers.
CLI integration under cli/.
Shared cross-entrypoint configuration and stage utilities.

What Does Not Belong Here

OpenAI endpoint-family route bodies and request helpers; those should move toward openai/<family>/ packages as part of #5227.
Generic model execution internals that belong under engine, worker, or model executor packages.

Some top-level utility files remain acceptable homes under Phase 0.2 (P0.2) of #5227. They are not part of the OpenAI helper migration unless explicitly referenced by #5227.