This commit introduces a new field, `is_embedding`, to the `SessionInfo` structure to clearly mark sessions running dedicated embedding models.
Key changes:
- Adds `is_embedding` to the `SessionInfo` interface in `AIEngine.ts` and the Rust backend.
- Updates the `loadLlamaModel` command signatures to pass this new flag.
- Modifies the llama.cpp extension's **auto-unload logic** to explicitly **filter out** and **not unload** any currently loaded embedding models when a new text generation model is loaded. This is a critical performance fix to prevent the embedding model (e.g., used for RAG) from being repeatedly reloaded.
Also includes minor code style cleanup/reformatting in `jan-provider-web/provider.ts` for improved readability.
* feat: Adjust RAM/VRAM calculation for unified memory systems
This commit refactors the logic for calculating **total RAM** and **total VRAM** in `is_model_supported` and `plan_model_load` commands, specifically targeting systems with **unified memory** (like modern macOS devices where the GPU list may be empty).
The changes are as follows:
* **Total RAM Calculation:** If no GPUs are detected (`sys_info.gpus.is_empty()` is true), **total RAM** is now set to $0$. This avoids confusing total system memory with dedicated GPU memory when planning model placement.
* **Total VRAM Calculation:** If no GPUs are detected, **total VRAM** is still calculated as the system's **total memory (RAM)**, as this shared memory acts as VRAM on unified memory architectures.
This adjustment improves the accuracy of memory availability checks and model planning on unified memory systems.
* fix: total usable memory in case there is no system vram reported
* chore: temporarily change to self-hosted runner mac
* ci: revert back to github hosted runner macos
---------
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Minh141120 <minh.itptit@gmail.com>
The KV cache size calculation in estimate_kv_cache_internal now includes a fallback mechanism for models that do not explicitly define key_length and value_length in the GGUF metadata.
If these attention keys are missing, the head dimension (and thus key/value length) is calculated using the formula embedding_length / total_heads. This improves robustness and compatibility with GGUF models that don't have the proper keys in metadata.
Also adds logging of the full model metadata for easier debugging of the estimation process.
* 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>
* feat: add getTokensCount method to compute token usage
Implemented a new async `getTokensCount` function in the LLaMA.cpp extension.
The method validates the model session, checks process health, applies the request template, and tokenizes the resulting prompt to return the token count. Includes detailed error handling for crashed models and API failures, enabling callers to assess token usage before sending completions.
* Fix: typos
* chore: update ui token usage
* chore: remove unused code
* feat: add image token handling for multimodal LlamaCPP models
Implemented support for counting image tokens when using vision-enabled models:
- Extended `SessionInfo` with optional `mmprojPath` to store the multimodal project file.
- Propagated `mmproj_path` from the Tauri plugin into the session info.
- Added import of `chatCompletionRequestMessage` and enhanced token calculation logic in the LlamaCPP extension:
- Detects image content in messages.
- Reads GGUF metadata from `mmprojPath` to compute accurate image token counts.
- Provides a fallback estimation if metadata reading fails.
- Returns the sum of text and image tokens.
- Introduced helper methods `calculateImageTokens` and `estimateImageTokensFallback`.
- Minor clean‑ups such as comment capitalization and debug logging.
* chore: update FE send params message include content type image_url
* fix mmproj path from session info and num tokens calculation
* fix: Correct image token estimation calculation in llamacpp extension
This commit addresses an inaccurate token count for images in the llama.cpp extension.
The previous logic incorrectly calculated the token count based on image patch size and dimensions. This has been replaced with a more precise method that uses the clip.vision.projection_dim value from the model metadata.
Additionally, unnecessary debug logging was removed, and a new log was added to show the mmproj metadata for improved visibility.
* fix per image calc
* fix: crash due to force unwrap
---------
Co-authored-by: Faisal Amir <urmauur@gmail.com>
Co-authored-by: Louis <louis@jan.ai>
Feature:
- Adjust homecreen and chatscreen for mobile device
- Fix tests for both FE and BE
Self-test:
- Confirm runnable on both Android and iOS
- Confirm runnable on desktop app
- All test suites passed
- Working with ChatGPT API
The Llama.cpp backend can emit the phrase “failed to allocate” when it runs out of memory.
Adding this check ensures such messages are correctly classified as out‑of‑memory errors,
providing more accurate error handling CPU backends.
* feat: Add model compatibility check and memory estimation
This commit introduces a new feature to check if a given model is supported based on available device memory.
The change includes:
- A new `estimateKVCache` method that calculates the required memory for the model's KV cache. It uses GGUF metadata such as `block_count`, `head_count`, `key_length`, and `value_length` to perform the calculation.
- An `isModelSupported` method that combines the model file size and the estimated KV cache size to determine the total memory required. It then checks if any available device has sufficient free memory to load the model.
- An updated error message for the `version_backend` check to be more user-friendly, suggesting a stable internet connection as a potential solution for backend setup failures.
This functionality helps prevent the application from attempting to load models that would exceed the device's memory capacity, leading to more stable and predictable behavior.
fixes: #5505
* Update extensions/llamacpp-extension/src/index.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update extensions/llamacpp-extension/src/index.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Extend this to available system RAM if GGML device is not available
* fix: Improve model metadata and memory checks
This commit refactors the logic for checking if a model is supported by a system's available memory.
**Key changes:**
- **Remote model support**: The `read_gguf_metadata` function can now fetch metadata from a remote URL by reading the file in chunks.
- **Improved KV cache size calculation**: The KV cache size is now estimated more accurately by using `attention.key_length` and `attention.value_length` from the GGUF metadata, with a fallback to `embedding_length`.
- **Granular memory check statuses**: The `isModelSupported` function now returns a more specific status (`'RED'`, `'YELLOW'`, `'GREEN'`) to indicate whether the model weights or the KV cache are too large for the available memory.
- **Consolidated logic**: The logic for checking local and remote models has been consolidated into a single `isModelSupported` function, improving code clarity and maintainability.
These changes provide more robust and informative model compatibility checks, especially for models hosted on remote servers.
* Update extensions/llamacpp-extension/src/index.ts
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Make ctx_size optional and use sum free memory across ggml devices
* feat: hub and dropdown model selection handle model compatibility
* feat: update bage model info color
* chore: enable detail page to get compatibility model
* chore: update copy
* chore: update shrink indicator UI
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Faisal Amir <urmauur@gmail.com>
This commit adds a new setting `llamacpp_env` to the llama.cpp extension, allowing users to specify custom environment variables. These variables are passed to the backend process when it starts.
A new function `parseEnvFromString` is introduced to handle the parsing of the semicolon-separated key-value pairs from the user input. The environment variables are then used in the `load` function and when listing available devices. This enables more flexible configuration of the llama.cpp backend, such as specifying visible GPUs for Vulkan.
This change also updates the Tauri command `get_devices` to accept environment variables, ensuring that device discovery respects the user's settings.
This change modifies how the API key is passed to the llama-server process. Previously, it was sent as a command line argument (--api-key). This approach has been updated to pass the key via an environment variable (LLAMA_API_KEY).
This improves security by preventing the API key from being visible in the process list (ps aux on Linux, Task Manager on Windows, etc.), where it could potentially be exposed to other users or processes on the same system.
The commit also updates the Rust backend to read the API key from the environment variable instead of parsing it from the command line arguments.
This commit introduces a new configuration option offload_mmproj to the llamacpp extension.
The offload_mmproj setting allows users to control whether the multimodal projector model is offloaded to the GPU. By default, it's offloaded for better performance. If set to false, the projector model will remain on the CPU, which can be useful in low GPU memory scenarios, though image processing might take longer.
Additionally, this commit adds validate_mmproj_path to ensure the provided --mmproj path is valid and accessible, preventing issues during model loading.
This change also refactors some invoke calls for improved readability.
