issues
search
davmacario
/
MDI-LLM
Implementation of Model-Distributed Inference for Large Language Models, built on top of LitGPT
MIT License
3
stars
2
forks
source link
Develop
#22
Closed
davmacario
closed
6 months ago
davmacario
commented
6 months ago
Changes:
Use threading.Event to wait for messages in the input queue at each node (no busy waiting anymore)
Reduce memory usage by deleting unused variables and possible copies
(Attempt to) improve program to monitor memory usage -
Not working
Add programs to produce plots for result comparison
Update readme and add images
Fix minor bugs/issues
Changes: