llama-stack-mirror/llama_stack/providers/inline/eval
Matthew Farrellee 7c888fc0da
feat: update eval runner to use openai endpoints (#3588)
# What does this PR do?

move the eval=inline::meta-reference implementation to use
openai_completion/openai_chat_completion

note: this breaks backward compatibility if eval setup used sampling
params' repetition_penalty or strategy

## Test Plan

ci w/ new recordings

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
2025-09-29 13:13:53 -07:00
..
meta_reference feat: update eval runner to use openai endpoints (#3588) 2025-09-29 13:13:53 -07:00
__init__.py Add missing init file 2024-12-05 17:44:14 -08:00