This is a refactoring PR. It updates the Jetstream/Pytorch version to a newer revision, that allows to pass the sampler function as parameter to the prefill and generate functions, as we requested. This simplifies our code, making the HfEngine usage redundant, so we can drop it.
What does this PR do?
This is a refactoring PR. It updates the Jetstream/Pytorch version to a newer revision, that allows to pass the sampler function as parameter to the
prefillandgeneratefunctions, as we requested. This simplifies our code, making theHfEngineusage redundant, so we can drop it.