vllm-omni

0 Fork 0

Files

T

tzhouamandClaude Fable 5.1 b22dcc59f7 [Edge][WP1] Add edge deploy profile and deploy_profile selector

* vllm_omni/deploy/edge/qwen3_tts.yaml: single-device Qwen3-TTS profile with a
  ramped codec chunk schedule (2->4->8->16->25 frames) that removes the ~80 ms
  playback stall of the default 1->25 schedule, decode batch 1, max_num_seqs 4.
* deploy_profile="edge" (Omni/AsyncOmni kwarg, --deploy-profile CLI, headless
  serve) resolves vllm_omni/deploy/<profile>/<model_type>.yaml; mutually
  exclusive with deploy_config; explicit profiles never fall back silently.
* tests/helpers/stage_config.py: modify_stage_config anchors a relative
  base_config before writing the temp YAML so overlay-derived configs resolve.
* async_omni_engine.py also carries the init-timeline hooks used by WP2.

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

2026-09-09 10:27:33 +08:00

fixtures

[CI]Split GPU jobs by cards_* and reject hand-written SKU marks (#6650 )

2026-08-29 18:42:33 +08:00

tests

[Model] Add native MAGI-2 Preview diffusion support (#5918 )

2026-09-05 15:32:30 +08:00

__init__.py

[CI] Select mirror_hardwares presets via MIRROR_HW (H100/B200) (#5543 )

2026-09-02 15:39:49 +00:00

assertions.py

[Model] Add native MAGI-2 Preview diffusion support (#5918 )