tzhouam f24273dc03 Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking. ...

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

2026-02-13 09:50:11 +00:00

..

offline_inference

Merge origin/main into dev/rebase-v0.16.0.

2026-02-12 21:18:03 +08:00

online_serving

Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking.

2026-02-13 09:50:11 +00:00