[Bug]: extra_headers are dropped from an embeddings request when provider is hosted_vllm/openai_like #13088
Description
What happened?
When provider is set to hosted_vllm/openai_like, embeddings requests are missing custom headers (see the code - no handling of extra_headers).
Relevant log output
Are you a ML Ops Team?
Yes
What LiteLLM version are you on ?
v.1.74.9
Twitter / LinkedIn details
No response