david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ dynatempagain

50h100a 8f5adc5a5e make function consistent with comments:		4 månader sedan
..
guided_decoding	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 månader sedan
layers	8f5adc5a5e make function consistent with comments:	4 månader sedan
model_loader	30d7effc7c feat: add siglip encoder for llava family (#626)	4 månader sedan
models	a0e446a17d feat: initial encoder-decoder support with BART model (#633)	4 månader sedan
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 månader sedan
_custom_op.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 månader sedan
pooling_metadata.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 månader sedan
sampling_metadata.py	93f82c8c01 bringing dynatemp back	4 månader sedan
utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 månader sedan