- updated project files
- added certifi to backend download and update checking
- add and fix type hints
- small file formatting changes
- update formatting of KV pairs to be cleaner
- update tensor data formatting and remove redundant KV pairs property
- add human readable mappings from KV pairs into model properties
- update CUDA backend check for latest llama.cpp format
- use urllib globally
- update llama.cpp python to `bc098c3` (now adds support for Qwen3, Llama 4, etc.)
- update requirements and general maint
- UI fixes in AutoGGUF
- Updated backend selection box to sort by newest version
- Fixed log information box inserting newlines on open and autoscroll
- Modified task deletion behavior
- Fixed logging for cancellation/deletion
- Updated readme information
- add AUTOGGUF_BACKEND_REPO environment variable to set GitHub repo to fetch releases
- remove Import Model confirmation
- fix error when deleting models from list
- add localizations and update README with message
- updated copyright year in LICENSE file to 2025
- bundled llama.cpp licensing text in About menu to maintain MIT compliance
- updated llama.cpp and gguf Python library and scripts
- adjusted monitoring intervals from 0.2s to 0.5s
- updated Python requirements to latest compatible versions
- added new HF to GGUF conversion types: `tq1_0` and `tq2_0`
Happy New Year 🎉!
- add clipboard support to save/load preset with shift clicking
- update README.md for clarity
- fixes incorrect menu bar name for Load Preset
- update Czech translations
- support shift clicking Quantize Model button to get quantize command
- clean up imports in AutoGGUF.py and add localization keys
- use str() for getting log_dir_name
- remove legacy validate_quantization_inputs() function
- add return_command parameter to quantize_model() function
- support specifying log directory name using AUTOGGUF_LOG_DIR_NAME environment variable
- update dependencies, except transformers due to a small regression
- use localizations for menubar
- bump AutoGGUF version to v2.0.0
- rename imports_and_globals.py to globals.py
- reformat code
- use file select for Merge/Split GGUF functions
- move general functions verify_gguf and process_args to globals.py
- create Plugins class for extensibility
- add RAM and CPU usage graphs
- add input validation using wraps
- reduce strictness of iMatrix status checking
- add right click context menu to models list
- improve startup time by optimizing default configuration (disable network fetches for backends and updates)
- add startup time measuring
- use localizations for .env loader
- use proper status in TaskListItem
- make sure to pass quant_threads and Logger to TaskListItem
- remove unnecessary logging in quantize_to_fp8_dynamic.py and optimize imports
- replace Flask with FastAPI and Uvicorn
- fix web page not found error
- port is now defaulted to 7001
- bind to localhost (127.0.0.1) instead of 0.0.0.0
- improve performance by using Uvicorn
- add OpenAPI docs for endpoints
- add more configuration options for AUTOGGUF_MODEL_DIR_NAME, AUTOGGUF_OUTPUT_DIR_NAME, and AUTOGGUF_RESIZE_FACTOR (these get created on startup)
- move some UI helper funtions out of AutoGGUF.py and into ui_update and Ta
- optimize imports for utility classes
- fix some missing imports
BuildTools