b5707

sycl: Cleanup codepaths in Get Rows in sycl backend (#14215)

Addresses unused reorder path

b5672

quantize : change int to unsigned int for KV overrides (#14197)

b5669

kv-cache : fix use-after-move of defrag info (#14189)

ggml-ci

b5663

compare-llama-bench: add option to plot (#14169)

* compare llama-bench: add option to plot

* Address review comments: convert case + add type hints

* Add matplotlib to requirements

* fix tests

* Improve comment and fix assert condition for test

* Add back default test_name, add --plot_log_scale

* use log_scale regardless of x_values

b5649

vocab : prevent heap overflow when vocab is too small (#14145)

ggml-ci

b5530

llama : add RobertaForSequenceClassification reranker support (#13875)

b5497

server: fix streaming crashes (#13786)

* add preludes to content on partial regex match

* allow all parsers to parse non-tool-call content.

* tweak order of <|python_tag|> vs <function= parsing for functionary v3.1 format. still not ideal but hopefully less prone to crash

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)