GitLab

enable gofmt/gofumpt/goimports/tenv

* Update docs

* token bug corrected

* Update docs/openai.md

* Update docs/openai.md

* add suffix

* merge conflicts

* merge conflicts

* docs without usage

* no usage

* rm metric note

* add prompt tokens to embed response

* rm slog

* metrics

* types

* prompt n

* clean up

* reset submodule

* add tokens to v1/embeddings

* separate usage

* OpenAI Docs

* Update docs/openai.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

* Remove newline

---------
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

Fix context in /api/generate grows too much (#5980).

refactor convert

fix modelfile message quotes

patches: phi3 optional sliding window attention

Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>

include modelfile messages

fix: environ lookup

Firebase Genkit

Better example for multi-modal input

* add prompt tokens to embed response

* rm slog

* metrics

* types

* prompt n

* clean up

* reset submodule

* update tests

* test name

* list metrics

Prevent partial loading on mixed GPU brands

In mult-brand GPU setups, if we couldn't fully load the model we
would fall through the scheduler and mistakenly try to load across
a mix of brands.  This makes sure we find the set of GPU(s) that
best fit for the partial load.