Saturday, June 13, 2026

Priorities

• Create Inference service prototype utilize t5-small machine learning model.

Work Log

Example Inference Service - t5-small ML Model

I created an example of an inference service using the t5-small ML model to translate from English to German.

I have written a blog post about how I deployed it at the following link:

https://ilyasahsan.xyz/blog/serve-t5-small-on-kubernetes-for-machine-learning-inference.html

Run the curl command below to test the service:

curl -s https://ilyasahsan.xyz/t5-small/inference/openai/v1/completions \
  -H 'Content-Type: application/json' \
  -d '{"model": "t5-small", "prompt": "translate English to German: The house is wonderful.", "stream":false, "max_tokens": 30 }'

Blockers

N/A

Carry-overs

• Create a playground to simulate the t5-small machine learning model.

Reflection

N/A