mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-30 19:29:59 +00:00
This adjusts the vllm openai_completion endpoint to also pass a value of 0 for prompt_logprobs, instead of only passing values greater than zero to the backend. The existing test_openai_completion_prompt_logprobs was parameterized to test this case as well. Signed-off-by: Ben Browning <bbrownin@redhat.com> |
||
|---|---|---|
| .. | ||
| client-sdk/post_training | ||
| external-provider/llama-stack-provider-ollama | ||
| integration | ||
| unit | ||
| verifications | ||
| __init__.py | ||