b5478

`server`: streaming of tool calls and thoughts when `--jinja` is on (…

b5476

releases : enable openmp in windows cpu backend build (#13756)

b5373

scripts : fix compare-llama-bench.py show parameter (#13514)

b5343

docs : Fix typo in InternVL3 model name (#13440)

b5269

llama : move end-user examples to tools directory (#13249)

* llama : move end-user examples to tools directory

---------

Co-authored-by: Xuan Son Nguyen <[email protected]>

b5215

model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architectur…

b5200

llama-bench : Add `--override-tensors` arg (#12922)

* Add --override-tensors option to llama-bench

* Correct llama-bench --override-tensors to --override-tensor

* llama-bench: Update --override-tensors parsing to match --tensor-split, appear in test matrix.

* Make new llama-bench util functions static to fix Ubuntu CI

* llama-bench: Correct -ot corner cases (No -ot calls, leading and trailing empty -ot spans, etc.)

b5191

llama : fix K-shift with quantized K and BLAS backend (#13113)

b5156

clip : refactor, add `image_manipulation` and `llava_uhd` classes (#1…

b5146

llama : recognize IBM Granite 3.3 FIM tokens (#12988)

The Granite's FIM tokens are very similar to Qwen's; it's just that
they use underscore instead of a dash. So <fim_middle> for example
instead of <fim-middle>.

Opening up tokenizer_config.json in ibm-granite/granite-3.3-8b-base
shows:

```
    "<fim_prefix>",
    "<fim_middle>",
    "<fim_suffix>",
    "<fim_pad>",
    ...
    "<reponame>",
```