GitLab

This reverts commit 5796bfc4.

* Revert "fix cmake build (#5505)"

This reverts commit 4fd5f352.

* llm: fix missing dylibs by restoring old build behavior

* crlf -> lf

* llm: put back old include dir

* llm: update link paths for old submodule commits

Always go build in CI generate steps

With the recent cgo changes, bugs can sneak through
if we don't make sure to `go build` all the permutations

This was leading to ambiguity and confusion in ollama.com, and is not
used anywhere in ollama at the moment. Once manifests are addressable by
digest, we can add this back in, and in a way that is more tailored to
the concept of addressing a manifest by digest.

* Use common prefix to select slot

* actually report `longest`

Prevent loading models larger than total memory

* Fix assert on small embedding inputs

* Update llm/patches/09-pooling.diff

Document older win10 terminal problems

Fix clip model loading with unicode paths

We haven't found a workaround, so for now recommend updating.

* Co-authored-by: Anatoli Babenia <anatoli@rainforce.org>
Co-authored-by: Maas Lalani <maas@lalani.dev>

Only set default keep_alive on initial model load

This change fixes the handling of keep_alive so that if client
request omits the setting, we only set this on initial load.  Once
the model is loaded, if new requests leave this unset, we'll keep
whatever keep_alive was there.

Users may not realize the siny new model they're trying to load
fits on their disk, but can't load into system+GPU memory.  Today
we crash, but with this fix, we'll give them a better error message
before even trying to load it.

Fix use_mmap for modefiles

* openai compatibility

* Revert "openai compatibility"

This reverts commit d3f98a811e00fc497d889c8c45b0cfec5b64690c.

* remove erroneous subtraction of prompt cache

Fix corner cases on tmp cleaner on mac

Better nvidia GPU discovery logging

When ollama is running a long time, tmp cleaners can remove the
runners.  This tightens up a few corner cases on arm macs where
we failed with "server cpu not listed in available servers map[]"

On windows, if the model dir contained unicode characters
clip models would fail to load.  This fixes the file name
handling in clip.cpp to support utf16 on windows.

Refine the way we log GPU discovery to improve the non-debug
output, and report more actionable log messages when possible
to help users troubleshoot on their own.

use model template by default