The user analytics platform for LLMs
Major release of ChatLLaMA solving multiple bugs and expanding the support to distrubuted training.
Major release for Nebullvm, adding support to diffusion model optimization.
Major release adding support to the diffusers
library.
This is a minor release fixing multiple bugs.
This is a minor release fixing multiple bugs.
This is a major release fixing multiple bugs and implementing two new functions for loading and saving the models.
Major release for Speedster adding the load_model
and save_model
functions.
mkdocs
This is a minor release modifying the metric_drop_ths
behaviour.
metric_drop_ths
by default set to 0.001
metric_drop_ths>0
metric_drop_ths>0.01
This is a minor release editing the default value for metric_drop_ths
and modifying the summarisation table at the end of the optimization.
This is a minor release editing the logs style.
This is a minor release adding tips and improving the logs.
This is a major release simplifying the backends installation and improving the UX.
shell not found
when installing TensorRT on specific Linux systems.Major release for Speedster, now supporting TF backend for HuggingFace transformers.
This release of Nebullvm modifies the structure of the library. Nebullvm library is transformed into a framework which can be used for building Apps for AI optimization. The end-to-end optimization tool is moved into speedster, an App built using nebullvm as underlying framework.
app/accelerate/speedster
.optimize_model
function in nebullvm
has been deprecated. It will be removed in the next major release.Speedster is the new library replacing the previous nebullvm API optimizing DL models in a single line of code. Speedster keeps the same interface as the previous nebullvm API.
optimize_model
function running from speedster import optimize_model
.