Reduce memory usage for large models (#61)
Signed-off-by:
Hung-Han (Henry) Chen <chenhungh@gmail.com>
Showing
- charts/ialacol/Chart.yaml 2 additions, 2 deletionscharts/ialacol/Chart.yaml
- charts/ialacol/templates/deployment.yaml 0 additions, 2 deletionscharts/ialacol/templates/deployment.yaml
- get_config.py 8 additions, 45 deletionsget_config.py
- get_llm.py 0 additions, 28 deletionsget_llm.py
- get_model_type.py 13 additions, 13 deletionsget_model_type.py
- log.py 12 additions, 0 deletionslog.py
- main.py 71 additions, 62 deletionsmain.py
- model_generate.py 70 additions, 4 deletionsmodel_generate.py
- streamers.py 66 additions, 4 deletionsstreamers.py
Loading
Please register or sign in to comment