Otto Bittner 2cf6705467 add vllm benchmark ...

The benchmark loads a small model
to allow running on many platforms
and to keep execution time low for
experimentation. It will make sense
to add a version to this test that
loads a larger model (e.g. llama3-8b).

2024-07-09 09:43:26 +02:00

..

Dockerfile.x86_64

add vllm benchmark

2024-07-09 09:43:26 +02:00