feat: add imdb and ag news dataset to datasets

feat: add spam or ham dataset for selection

feat: add some instructions to readme

feat: plots for llama and llama

feat: plots for gemma and haiku

feat: improved plots for gemma and o4mini comparison

chore: cleanup analyse notebook

chore: started with analysis notebook cleanup

feat: changed plot type for policy performance evaluation

feat: prepared tables and queue length plots for policy evaluation in report

chore: separate fabians and philips analysis notebooks

fix: merge conflict

Merge branch 'main' of github.com:fabianHueni/UNIBE_MSGAI_HS25_Project

feat: added policy performance analysis

Merge remote-tracking branch 'origin/main'

feat: add analysis for report

feat: added performance model parameters to UI instead of hardcoding

fix: logging issues because of type conflict that was introduced when adding new scheduler

result: added experiment with jseq scheduler, gemma on device and 4o-mini on cloud

feat: added jseq scheduler to javascript app

feat: comparing inference schedulers to experient measurements

feat: inference scheduler comparison

feat: implemented a simulation with the Join the Shortest Expected Queue (JSEQ) policy

feat: added a boolq stream simulator which can test our estimated model setup with the defined scheduler. we need to add queue size for on-device/cloud to the policy in order to make it really usable

feat: simulated different lambdas for the granite model

feat: built model to simulate different workloads

feat: validated the analytical solution with a simulation

feat: queueing model with manipulated on-device inference time to estimate optimal threshold for scheduler policy

Merge branch 'main' of github.com:fabianHueni/UNIBE_MSGAI_HS25_Project

chore: moved analyze split strategy function to utils

feat: add latency metrics for cloud

analyse: started with queueing model analysis for input character threshold decision

feat: add method to compute statistics for baseline experiments

feat: setup requirements.txt and uv env for analyse

results: split nicolas result in multiple folders

results: add results of qwen model

results: experimentes with 1070 gpu

fix: added error catch in request manager, adjusted cloud service getModelName method and inserted a console log for the no_think add-on

results: on-device results for lenovo_privat

results: cloud results for gemini 2.5 flahs and claude haiku 4.5

Merge branch 'main' of https://github.com/fabianHueni/UNIBE_MSGAI_HS25_Project

results: cloud results

Merge branch 'main' of github.com:fabianHueni/UNIBE_MSGAI_HS25_Project

anaylse: visualized distributions of timing metrics and analysed correlation inferencetime vs inputsize

fix: fixed qwen3 check to check first if service.getModelName() is defined

Merge branch 'main' of https://github.com/fabianHueni/UNIBE_MSGAI_HS25_Project

results: added results of 3 models with my lenovo büro laptop

analyse: updated analysis

Merge branch 'main' of github.com:fabianHueni/UNIBE_MSGAI_HS25_Project

analyse: started with data analysis