GitLab

Add native support for converting Qwen2 family models (including Qwen2.5)
from safetensors to gguf format so we can run it.

chore: upgrade to gods v2

* Add CUSTOM_CPU_FLAGS.

* fix golangci-lint error.

---------
Co-authored-by: Richard Lyons <rick@frob.com.au>

These fields are deprecated, but specifying them will not do anything. Removing them as the other deprecated fields will still work, but these do not, so they dont match our existing pattern.

Replaces `POST /api/create` to use JSON instead of a Modelfile.

This is a breaking change.

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

gods v2 uses go generics rather than interfaces which simplifies the
code considerably

This change adds a test to catch a regression in schema_to_grammar where
the order of keys in the JSON schema is not preserved in the generated
grammar, which is critical for step-by-step reasoning.

Sometimes the KV cache requires defragmentation even without
triggering the threshold heuristic. In this case, decoding
will not being able to find a KV cache slot. This is particularly
difficult for the caller to handle if it happens in between
ubatches. To avoid this, we should immediately trigger a defrag.

In addition, a heavily fragmented cache can require more than
max_moves to defragment. Currently, we stop when we hit the limit
but this can leave a cache that still does not have adequate space
even after defragmentation is triggered. Instead, we should do
multiple batches of processing until everything is complete.

Fixes #7949

This fixes another regression in the previous commit that fixed other
known bugs.