Modules:
| Name | Description |
|---|---|
api_server | |
chat_completion | |
cli_args | This file contains the command line arguments for the vLLM's |
engine | |
orca_metrics | Utility functions that create ORCA endpoint load report response headers. |
parser | |
run_batch | |
serving_completion | |
serving_models | |
serving_responses | |
serving_transcription | |
speech_to_text | |
utils | |