GitLab

add new enum values and improve MIN_BATCH_INFERENCE_SIZE documentation in pipeline_analyze.py

fix: include server_url in model key for backend model retrieval in vlm_analyze.py

fix: refine model path condition for transformers and sglang-engine backends in vlm_analyze.py

fix: correct syntax error in demo.py for VLM client backend

master->dev

update doc

update doc

Release 2.0.3

fix: update sglang version to 0.4.7 and adjust changelog for compatibility issues

master->dev

Release 2.0.2

Dev

master->dev

Release 2.0.1

fix: update configure_model to use environment variable for config file name