IlyaMescheryakov1402 4d0368da27 fix serving_num_processes

2024-07-25 12:52:27 +03:00

..

__init__.py

ClearML-Serving v2 initial working commit

2022-03-06 01:25:56 +02:00

Dockerfile

Upgrade to python 3.11

2023-04-12 23:38:56 +03:00

endpoints.py

Add Triton support for variable length requests, adds support for HuggingFace Transformers

2022-09-02 23:41:54 +03:00

entrypoint.sh

initial commit

2024-04-16 00:54:35 +03:00

init.py

initial commit

2024-04-16 00:54:35 +03:00

main.py

add OOM handler for MIG profiles

2024-05-30 00:58:17 +03:00

model_request_processor.py

initial commit

2024-04-16 00:54:35 +03:00

preprocess_service.py

Fix python < 3.10 support

2024-02-27 09:45:32 +02:00

requirements.txt

fix serving_num_processes

2024-07-25 12:52:27 +03:00

uvicorn_mp_entrypoint.py

Optimize async processing for increased speed

2022-10-08 02:12:04 +03:00