Deep Gandhi

Move api requirements to use pyproject groups

1

- [x] tested on mac - [x] tested on nvidia - [x] tested on amd

- Right now if you switch teams, there will be a reload but if no experiment is selected and you select an experiment, it doesnt automatically update and you need...

- This fixes the placeholder jobs we show as soon as we press Queue on Tasks tab - This also fixes useSWRWithAuth to accept options so refresh interval and other...

Set lab context var for org id in a subprocess correctly

1

- [x] Downloading models logic - [x] Plugins run - [x] Inference subprocess - [x] Other subprocess sweep

I tried to run the Orpheus model and this is what it did on its own: ``` ## Plugin unsloth_text_to_speech_server installed successfully. 🏃 Loading Inference Server for canopylabs/orpheus-3b-0.1-ft with {'inferenceEngine':...

A user Frank talked to mentioned they primarily like the GPU splitting feature when doing inference with models in LM Studio. We should add that as well. This may involve...

- TheRock (https://github.com/ROCm/TheRock) is a new system by ROCm for building ROCm on your system. Having this would enable us to also install ROCm for users solving numerous problems faced...

We have a long list of allowed architectures in diffusion router, we should use a diffusers method instead to decide the architecture and whether it should be allowed or not

``` Virtual environment found, using it for evaluation... Running command: $ /home/transformerlab/.transformerlab/workspace/plugins/common-eleuther-ai-lm-eval-harness/venv/bin/python -m lm_eval --model hf --model_args pretrained=/home/transformerlab/.transformerlab/workspace/models/SmolLM2-135M_dummy-multi,trust_remote_code=True --tasks mmlu_abstract_algebra --device cuda:0 --trust_remote_code --log_samples --limit 0.05 --output_path /home/transformerlab/.transformerlab/workspace/experiments/alpha/evals/SplendidCheetah/395 --Beginning to...