`core.inference.text_generation_server.dynamic_text_gen_server.flask_server`#

Module Contents#

Functions#

`temp_log_level`	Enables temporarily overriding the logging level.
`run_flask_server`	Initializes and runs the async Flask server.

Data#

API#

core.inference.text_generation_server.dynamic_text_gen_server.flask_server.logger#: ‘getLogger(…)’

core.inference.text_generation_server.dynamic_text_gen_server.flask_server.temp_log_level(level, logger=None)#: Enables temporarily overriding the logging level.

async core.inference.text_generation_server.dynamic_text_gen_server.flask_server.run_flask_server( coordinator_port: int, tokenizer, rank: int, flask_port: int, )#: Initializes and runs the async Flask server.