llama-stack-mirror/llama_stack/providers/remote/inference/vllm
Ben Browning 8f5cd49159 vllm prompt_logprobs can also be 0
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>
2025-04-09 17:32:03 -04:00
..
__init__.py Fix precommit check after moving to ruff (#927) 2025-02-02 06:46:45 -08:00
config.py fix: Add the option to not verify SSL at remote-vllm provider (#1585) 2025-03-18 09:33:35 -04:00
vllm.py vllm prompt_logprobs can also be 0 2025-04-09 17:32:03 -04:00