* build: bump max python to 3.13

* build: isolate realesrgan in a extra because no 3.13 basicsr wheels are available

…form usage (#616)

* feat: implement llama.cpp algorithm

* feat: llama.cpp conversion by forcing f16 for tiny models and bypass device checks for llama-cpp models due to a lack of model.parameters() support

* fix: preserve enum membership for callables in engine to support Python 3.13

- addressed functools.partial object compatability with py 3.13
- integrated enum.member() in SAVE_FUNCTIONS and LOAD_FUNCTIONS
- updated the LlamaCpp algorithm implementation to utilize the standardized
  naming convention.
- cleaned up redundant commented-out logic in the save_pruna_model function.

Verified through restoration of LlamaCpp integration tests and diagnostic
scripts confirming Enum member registration.

* feat: integrate Llama.cpp and enhance engine stability for cross-platform usage

- standardized LlamaCpp implementation and naming conventions within the engine
- implemented cache directory cleanup to prevent shutdown errors on Windows
- added a save() alias to the base model wrapper for improved API consistency
- updated project configuration with Llama.cpp and dependency group
- benchmarked using SmolLM2-135M-Instruct with q4_k_m quantization

* fix: integrity verification of remote scripts

* fix: ruff typechecking and shutil.move on GGUF file handling

* feat: updated llama support with rebased head branch commits
- added Int class for integer-based configuration.
- updated get_device and model_checks for llama_cpp.
- implemented secure conversion script caching.
- enabled TestLlamaCpp and removed manual test overrides.

* fix: ruff check fixes and llama_cpp updates

* refactor: llama_cpp code length update and extra comments for visibility

* refactor: code complexity

* refactor: removed dead code from save_model_llama_cpp in save.py

* feat: initial implementation for rapidata (#581)

* feat: initial implementation for rapidata

* ci: add rapidata dependency and some cleanup

* Guard optional rapidata metric import and tighten validation

Applied via @cursor push command

* refactor: address PR comments

* feat: add polling and address further PR comments

* refactor: add mixin for setting context

* ci: add evaluation as an umbrella dep

* refactor: address PR comments

* ci: separate rapidata matrix

* fix: minor issues

* ci: make tests import safe

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>

* refactor: required review changes and additional comments to address llama.cpp compatibility

* fix: subprocess run updates to prevent injection vulnerabilities

* build: bump python 3.13 (#624)

* build: bump max python to 3.13

* build: isolate realesrgan in a extra because no 3.13 basicsr wheels are available

* feat(llama_cpp): update conversion script and improve tokenizer fallbacks
- Pinned convert_hf_to_gguf.py to tag b8958
- Added automated model tokenizer resolution logic
- Introduced .get() operators to SmashConfig wrappers
- Refactored pyproject.toml

* fix: updated llama_cpp default hyperparameters and save logic

* fix: temp directory cleanup and ruff check

* feat: integrate llama_cpp algorithm backend and update conversion version
- Update ggml-org/llama.cpp conversion script to version tag b9670
- Register llamacpp in CI tests.yaml workflows matrix
- Add pruna[llamacpp] to optional dev deps

* fix: load llama.cpp config settings and support unwrapped PrunaModel device retrieval
- Apply n_gpu_layers and main_gpu config settings during llama_cpp model reload
- Unwrap PrunaModel wrappers in get_device to retrieve internal device of llama.cpp models correctly

* fix: latest conversion script version has been refactored, need to pin older one

* fix: rebuild llama-cpp-python from source on pruna cpu runners

* fix: rebase on main that just changed CI

* fix: solve llamacpp symetry compatibility

---------

Co-authored-by: Begüm Çığ <begumcig@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Gaspar Rochette <gaspar.rochette@pruna.ai>
Co-authored-by: llcnt <73026329+llcnt@users.noreply.github.com>