PR #920 Fix prompt caching on llama.cpp endpoints

Fix prompt caching on llama.cpp endpoints #920

nsarrazin merged 2 commits into huggingface:main from reversebias:fix/llama_cpp_prompt_caching

Explicitly enable prompt caching on llama.cpp endpoints

0b3e42a5

nsarrazin approved these changes on 2024-03-11

Merge branch 'main' into fix/llama_cpp_prompt_caching

79549238

nsarrazin merged eb071be4 into main 2 years ago

Reviewers

nsarrazin

Assignees

No one assigned

Labels

None yet

Milestone

No milestone