Van Pham
Van Pham
- Cortex as extension -> 3 engine along side with Nitro => allow Jan calling Cortex API (only chat completion) - Llamacpp: bundle with jan app, download by default -...
- Cortex extensions output to app.log - Label log records per engines [APP] [NITRO] [CORTEX] - Inline error within thread, and troubleshooting assistance remains unchanged
This is just a draft idea: - [ ] fetch the list of URL for models download, and verify it's valid (to avoid broken download in Jan hub) - [...
Description: The current model ID is not visible in the local API server, making it challenging for users to efficiently create API requests. Proposed Solution: Implement a way to view...
**Describe the bug** A clear and concise description of what the bug is. **Expected behavior** > Auto-hide Scroll Bars > Turn this ON to hide scrollbars by default, and only...
## Resources - #1125 ## Original Post - [ ] Focus team on basic functionality - e.g. install, inference call - [ ] Out-of-scope: model testing (for now) **Problem** To...
**Describe the bug** When generating responses using a local llm, cortex-cpp still seems to use CPU. https://discord.com/channels/1107178041848909847/1149558035971321886/1253148982188838954 **To Reproduce** 1. Install cortex-cpp and the CUDA toolkit locally. 2. Turn on...
**Description:** The arch detector in the system is not functioning properly, leading to the introduction of special characters in the GPU name within the `settings.json` file. Specifically, the GPU name...
## Motivation - Enhance user experience by offering support for multiple languages, catering to a diverse user base and expanding the reach of the product. ## Specs - Implement multilingual...