0 Fork 0

Files

T

e6cebf8557 [Bugfix][Omni-DuplexEval] Load local Hugging Face dataset layouts in duplex eval loader (#7331 )

Signed-off-by: RyanYun09 <RyanYun09@users.noreply.github.com>
Co-authored-by: RyanYun09 <RyanYun09@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

2026-09-16 20:05:52 +08:00

__init__.py

[Benchmark] Add vLLM-Omni Omni model online benchmark (#780 )

2026-01-30 11:41:09 +08:00

base.py

[Refactor] Split vllm_omni/entrypoints/cli/benchmark/serve.py (#5206 )

2026-07-23 16:00:32 +00:00

cli_args.py

[Core][Frontend] Unified Full-duplex Framework (#7413 )

2026-09-16 15:35:36 +08:00

main.py

[Refactor] Split vllm_omni/entrypoints/cli/benchmark/serve.py (#5206 )

2026-07-23 16:00:32 +00:00

omni_duplex_eval.py

[Bugfix][Omni-DuplexEval] Load local Hugging Face dataset layouts in duplex eval loader (#7331 )

2026-09-16 20:05:52 +08:00

README.md

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

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

serve.py

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

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

README.md

Benchmark CLI

This package owns Omni benchmark subcommands exposed through the CLI.

What Belongs Here

CLI parser extensions for benchmark commands.
Benchmark command dispatch.
Benchmark-only argument groups.

What Does Not Belong Here

Runtime server route helpers.
OpenAI endpoint implementation details.
Benchmark execution internals that belong under vllm_omni.benchmarks.

This package is not part of the OpenAI endpoint helper migration. It may need import updates only if CLI/bootstrap ownership changes during #5227.