Taichang Zhou c8b695f181 smaller talker gpu util to avoid oom ...

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>

2026-03-08 01:48:42 +08:00

..

offline_inference

Replace hard-coded cuda generator with current_omni_platform.device_type (#1677)

2026-03-05 06:53:30 +00:00

online_serving

Change pytest fixture scope from "module" to "class" for omni_server and omni_server_no_async_chunk in test_qwen3_tts.py to improve test isolation and resource management.

2026-03-07 14:50:59 +08:00

stage_configs

smaller talker gpu util to avoid oom

2026-03-08 01:48:42 +08:00

__init__.py

[ROCm] [CI] Add ROCm Dockerfile and AMD CI (vllm v0.12.0) (#280)

2025-12-21 11:51:37 +08:00