* feat: move estimateKVCacheSize to BE
* feat: Migrate model planning to backend
This commit migrates the model load planning logic from the frontend to the Tauri backend. This refactors the `planModelLoad` and `isModelSupported` methods into the `tauri-plugin-llamacpp` plugin, making them directly callable from the Rust core.
The model planning now incorporates a more robust and accurate memory estimation, considering both VRAM and system RAM, and introduces a `batch_size` parameter to the model plan.
**Key changes:**
- **Moved `planModelLoad` to `tauri-plugin-llamacpp`:** The core logic for determining GPU layers, context length, and memory offloading is now in Rust for better performance and accuracy.
- **Moved `isModelSupported` to `tauri-plugin-llamacpp`:** The model support check is also now handled by the backend.
- **Removed `getChatClient` from `AIEngine`:** This optional method was not implemented and has been removed from the abstract class.
- **Improved KV Cache estimation:** The `estimate_kv_cache_internal` function in Rust now accounts for `attention.key_length` and `attention.value_length` if available, and considers sliding window attention for more precise estimates.
- **Introduced `batch_size` in ModelPlan:** The model plan now includes a `batch_size` property, which will be automatically adjusted based on the determined `ModelMode` (e.g., lower for CPU/Hybrid modes).
- **Updated `llamacpp-extension`:** The frontend extension now calls the new Tauri commands for model planning and support checks.
- **Removed `batch_size` from `llamacpp-extension/settings.json`:** The batch size is now dynamically determined by the planning logic and will be set as a model setting directly.
- **Updated `ModelSetting` and `useModelProvider` hooks:** These now handle the new `batch_size` property in model settings.
- **Added new Tauri commands and permissions:** `get_model_size`, `is_model_supported`, and `plan_model_load` are new commands with corresponding permissions.
- **Consolidated `ModelSupportStatus` and `KVCacheEstimate`:** These types are now defined in `src/tauri/plugins/tauri-plugin-llamacpp/src/gguf/types.rs`.
This refactoring centralizes critical model resource management logic, improving consistency and maintainability, and lays the groundwork for more sophisticated model loading strategies.
* feat: refine model planner to handle more memory scenarios
This commit introduces several improvements to the `plan_model_load` function, enhancing its ability to determine a suitable model loading strategy based on system memory constraints. Specifically, it includes:
- **VRAM calculation improvements:** Corrects the calculation of total VRAM by iterating over GPUs and multiplying by 1024*1024, improving accuracy.
- **Hybrid plan optimization:** Implements a more robust hybrid plan strategy, iterating through GPU layer configurations to find the highest possible GPU usage while remaining within VRAM limits.
- **Minimum context length enforcement:** Enforces a minimum context length for the model, ensuring that the model can be loaded and used effectively.
- **Fallback to CPU mode:** If a hybrid plan isn't feasible, it now correctly falls back to a CPU-only mode.
- **Improved logging:** Enhanced logging to provide more detailed information about the memory planning process, including VRAM, RAM, and GPU layers.
- **Batch size adjustment:** Updated batch size based on the selected mode, ensuring efficient utilization of available resources.
- **Error handling and edge cases:** Improved error handling and edge case management to prevent unexpected failures.
- **Constants:** Added constants for easier maintenance and understanding.
- **Power-of-2 adjustment:** Added power of 2 adjustment for max context length to ensure correct sizing for the LLM.
These changes improve the reliability and robustness of the model planning process, allowing it to handle a wider range of hardware configurations and model sizes.
* Add log for raw GPU info from tauri-plugin-hardware
* chore: update linux runner for tauri build
* feat: Improve GPU memory calculation for unified memory
This commit improves the logic for calculating usable VRAM, particularly for systems with **unified memory** like Apple Silicon. Previously, the application would report 0 total VRAM if no dedicated GPUs were found, leading to incorrect calculations and failed model loads.
This change modifies the VRAM calculation to fall back to the total system RAM if no discrete GPUs are detected. This is a common and correct approach for unified memory architectures, where the CPU and GPU share the same memory pool.
Additionally, this commit refactors the logic for calculating usable VRAM and RAM to prevent potential underflow by checking if the total memory is greater than the reserved bytes before subtracting. This ensures the calculation remains safe and correct.
* chore: fix update migration version
* fix: enable unified memory support on model support indicator
* Use total_system_memory in bytes
---------
Co-authored-by: Minh141120 <minh.itptit@gmail.com>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
* ci: update artifact name for Linux and Windows build
* ci: enhance logic for naming convention for mac, linux and windows builds
* fix: resolve nested template expression in artifact names
- pulls fix for #5463 out of the github release workflow and into
the make/yarn build process
- implements a wrapper script that pins linuxdeploy and injects
a new location for XDG_CACHE_HOME into the build pipeline,
allowing manipulating .cache/tauri without tainting the hosts
.cache
- adds ./.cache (project_root/.cache) to make clean and mise clean
task
- remove .devcontainer/buildAppImage.sh, obsolete now that extra
build steps have been removed from the github workflow and
incorporated in the normal build process
- remove appimagetool from .devcontainer/postCreateCommand.sh,
as it was only used by .devcontainer/buildAppImage.sh
- pulled appimage packaging steps out of release workflow into new
src-tauri/build-utils/buildAppImage.sh
- cleaned up yarn scripts:
- moved multi platform yarn scripts out of yarn build:tauri:<platform>
into generic yarn build:tauri
- split yarn build:tauri:linux:win32 into separate yarn scripts so it's
clearer what is specific to which platform
- added src-tauri/build-utils/buildAppImage.sh to new yarn build:tauri:linux
yarn script
This is also a good entry point to add flatpak builds in the future.
Part of #5641
Allows for better per platform default config. Currently the
default serves windows/macos fine while it has to be tweaked
in order to build for linux
make build-tauri now successfully runs where it errored out before.
Appimages made with make alone however is incomplete as there are
still post processing steps in the github release workflow to bundle
additional resources.
- split platform specific config out of tauri.conf.json into auxiliary
platform specific config files, natively supported by tauri
- pull improved defaults out of template-tauri-build-linux-x64.yml
into new tauri.linux.conf.json
- fix tauri-build-linx-x64.yml to utilize new tauri.linux.conf.json
* chore: remove legacy themes
* refactor: clean up dependencies
* chore: remove cuda 11 dependency - fix linux LD_LIBRARY_PATH
* fix: load models issue on Linux
# Conflicts:
# src-tauri/src/core/setup.rs
* chore: do not download cuda 11 by default
* chore: remove cuda 11 from installer
* fix: cuda lookup on Linux
* refactor: deprecate legacy packages and clean up build scripts
* chore: remove joi publish workflow
* chore: core publish run on dispatch only
* chore: correct version bump on web package
* chore: make dev for tauri target
