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). @ dry

AlpinDale a11dee6352 wip		il y a 4 mois
..
guided_decoding	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
layers	a11dee6352 wip	il y a 4 mois
model_loader	8e22069c9e fix: weight loading for scalars (#718)	il y a 4 mois
models	08711d2ac9 feat: add Exaone model support (#743)	il y a 4 mois
__init__.py	7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666)	il y a 4 mois
_custom_op.py	5d37ec1016 suppress tpu import warning (#696)	il y a 4 mois
parameter.py	4f6020cc86 chore: migrate gptq_marlin to AphroditeParameters (#699)	il y a 4 mois
pooling_metadata.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
sampling_metadata.py	a11dee6352 wip	il y a 4 mois
utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	il y a 8 mois