0 Fork 0

Files

T

Mu GuanLinandHongsheng Liu 3a82c85880 [Experimental][Perf] Eliminate redundant host copies from generated-video transport (#7355 )

Signed-off-by: mglyn <1203789601@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-09-30 11:37:57 +08:00

benchmark

[Frontend][Benchmark] Add judger and accuracy metrics for OmniInterac… (#7317 )

2026-09-24 08:34:23 +00:00

__init__.py

[Benchmark][MiniCPM-o] Add Omni-DuplexEval support (#6634 )

2026-08-27 16:31:50 +08:00

logo.py

[Bugfix] Fix missing ANSI colors in CLI logo when output is piped (#1636 )

2026-05-06 15:43:19 +00:00

main.py

[Rebase] Rebase to vllm 0.23.0 (#4286 )

2026-06-13 16:43:02 +00:00

README.md

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

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

serve.py

[Experimental][Perf] Eliminate redundant host copies from generated-video transport (#7355 )

2026-09-30 11:37:57 +08:00

README.md

CLI Entrypoints

This package owns vLLM-Omni command-line integration.

What Belongs Here

Omni CLI command registration and dispatch.
CLI argument parsing and validation for vllm ... --omni.
Headless/runtime launch wiring that ultimately calls server bootstrap code.
CLI-only presentation helpers such as the logo.

What Does Not Belong Here

FastAPI route bodies.
OpenAI endpoint request helpers.
Server app utilities that are shared outside CLI; those belong under entrypoints/serve.

The CLI currently imports openai.api_server.omni_run_server. If server bootstrap moves later, update this import, but do not fold route helpers into the CLI package. Related endpoint cleanup is tracked by #5227.