llama-stack
llama-stack copied to clipboard
Adding Snowflake Provider Support + Distribution Template
Adds support for inference with Snowflake's Cortex endpoint. See docs for more background on Cortex:https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-llm-rest-api
Testing
- built a new stack from scratch using remote::snowflake for the Inference API
- ran
python -m llama_stack.apis.inference.client localhost - directly submitted request to the llama stack server