[Core] Add engine option to return only deltas or final output (#7381)

This commit is contained in:
Nick Hill
2024-09-12 20:02:00 +01:00
committed by GitHub
parent a6c0f3658d
commit 551ce01078
10 changed files with 371 additions and 137 deletions

View File

@@ -50,6 +50,7 @@ steps:
- tests/worker
commands:
- pytest -v -s async_engine # Async Engine
- NUM_SCHEDULER_STEPS=4 pytest -v -s async_engine/test_async_llm_engine.py
- pytest -v -s test_inputs.py
- pytest -v -s multimodal
- pytest -v -s test_utils.py # Utils