b4431

llama-run : fix context size (#11094)

Set `n_ctx` equal to `n_batch` in `Opt` class. Now context size is
a more reasonable 2048.

Signed-off-by: Eric Curtin <[email protected]>

b4404

ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)

* Fixes for clang AVX VNNI

* enable AVX VNNI and alder lake build for MSVC

* Apply suggestions from code review

---------

Co-authored-by: slaren <[email protected]>

b4381

llama : support InfiniAI Megrez 3b (#10893)

* Support InfiniAI Megrez 3b

* Fix tokenizer_clean_spaces for megrez

b4349

tests: add tests for GGUF (#10830)

b4334

llava : Allow locally downloaded models for QwenVL (#10833)

* Allow locally downloaded models for QwenVL

* Define model_path

* rm trailing space

---------

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

b4318

ggml : Fix compilation issues on ARM platform when building without f…

b4302

ggml: load all backends from a user-provided search path (#10699)

* feat: load all backends from a user-provided search path

* fix: Windows search path

* refactor: rename `ggml_backend_load_all_in_search_path` to `ggml_backend_load_all_from_path`

* refactor: rename `search_path` to `dir_path`

* fix: change `NULL` to `nullptr`

Co-authored-by: Diego Devesa <[email protected]>

* fix: change `NULL` to `nullptr`

---------

Co-authored-by: Diego Devesa <[email protected]>

b4229

readme : remove old badge

b4215

ggml : remove redundant copyright notice + update authors

b4201

Add some minimal optimizations for CDNA (#10498)

* Add some minimal optimizations for CDNA

* ggml_cuda: set launch bounds also for GCN as it helps there too