vllm-omni

0 Fork 0

Files

T

tzhouamandClaude Fable 5.1 502dd7bed0 [edge-infer W8] Serving e2e launches the server itself; no module-level fcntl on the serve import path

test_e2e_serve_text.py no longer imports tests.helpers.runtime (it pulls
the media/diffusion test helpers and therefore diffusers, absent from the
Windows venv); a small Popen launcher with a psutil process-tree kill
replaces OmniServer for this one test.

vllm-omni serve died at import on Windows: entrypoints/cli imports
benchmarks.patch -> benchmarks/omniinteract.py, which did 'import fcntl'
at module scope. Its output lock is rebuilt on the fork's
_filelock_compat primitive (fcntl on POSIX, msvcrt on Windows).
engine/stage_phase_lock.py (parallel_stage_init's SH/EX device locks)
gets the same treatment: fcntl optional, modes spelled locally, and on
Windows both modes map to the exclusive byte lock -- more serialising,
never less safe. Measured: the serving e2e's server exited with
ModuleNotFoundError: No module named 'fcntl' on both Windows venvs.

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

2026-09-18 19:05:55 +08:00

local

[edge-infer W8] Serving e2e launches the server itself; no module-level fcntl on the serve import path

2026-09-18 19:05:55 +08:00

__init__.py

[Edge][WP4] Add hardware adaptation: probe, derived overrides, auto profile, calibration

2026-09-09 11:01:40 +08:00

test_adapt.py

[Edge][WP4] Add hardware adaptation: probe, derived overrides, auto profile, calibration

2026-09-09 11:01:40 +08:00

test_auto_profile.py

[Edge][WP4] Add hardware adaptation: probe, derived overrides, auto profile, calibration