tzhouamandClaude Fable 5.1 97d97b6503 [edge-infer W8] Omni serve CLI: uvloop optional, selector-loop asyncio.run on Windows ...

uvloop ships no Windows wheels, so 'import uvloop' at module scope in
entrypoints/cli/serve.py killed vllm-omni serve on Windows at import
(measured in the serving e2e after the fcntl fix). _run_forever() uses
uvloop where present and asyncio.run on WindowsSelectorEventLoopPolicy
otherwise, which zmq.asyncio needs. The remaining serve-import blocker
on the Windows venv was a missing dependency, torchaudio (vLLM's own
requirement), installed into the venvs rather than patched.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-18 19:09:22 +08:00

..

benchmark

[Bugfix] Bound omni benchmark per-request timeout to 15 min by default (#7130)

2026-09-08 02:00:25 -07:00

__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

serve.py

[edge-infer W8] Omni serve CLI: uvloop optional, selector-loop asyncio.run on Windows

2026-09-18 19:09:22 +08:00