v3.21
Make /v1/embeddings functional, add request/response types
mtmd: Fix /chat/completions for llama.cpp
Openai embedding fix to support jina-embeddings-v2 (#4642)
extensions/openai: Fixes for: embeddings, tokens, better errors. +Docs update, +Images, +logit_bias/logprobs, +more. (#3122)
Image: Several fixes
New llama.cpp loader (#6846)
Properly fix the /v1/models endpoint
Lint
Image: Simplify the API code, add the llm_variations option
Add types to the encode/decode/token-count endpoints
Fix API requests always returning the same 'created' time