support JSON request payload passed to LLM service layer

This commit is contained in:
Adam Wilson
2025-04-23 16:09:05 -06:00
parent 264f332c10
commit 8c6f38db31
4 changed files with 47 additions and 24 deletions
+6 -4
View File
@@ -28,9 +28,11 @@ jobs:
huggingface-cli download microsoft/Phi-3-mini-4k-instruct-onnx --include cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/* --local-dir .
pip install onnxruntime-genai
# curl https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/phi3-qa.py -o phi3-qa.py
python ${{ github.workspace }}/tests/llm/phi3_language_model.py \
--prompt 'Describe the principle of existence, from the first principles of philosophy.' \
-m cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4 \
# python ./tests/llm/phi3_language_model.py --prompt 'Describe the principle of existence, from the first principles of philosophy.' -m cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4
# python ${{ github.workspace }}/tests/llm/phi3_language_model.py \
# --prompt 'Describe the principle of existence, from the first principles of philosophy.' \
# -m cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4
- name: Run REST API server
run: |
@@ -38,4 +40,4 @@ jobs:
- name: Test API call
run: |
curl -X POST -i localhost:9999 -d '{ "key":"123456789" }'
curl -X POST -i localhost:9999 -d '{ "prompt": "describe a random planet in our solar system in 10 words or less" }'