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). @ linear_weights_light

Light 7589af22c9 Try to fix gguf.		hai 7 meses
..
attention	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
common	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
distributed	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
endpoints	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
engine	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
executor	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	hai 10 meses
lora	37cf11c19a part 1	hai 8 meses
modeling	7589af22c9 Try to fix gguf.	hai 7 meses
processing	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
quantization	7589af22c9 Try to fix gguf.	hai 7 meses
spec_decode	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
task_handler	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
transformers_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	hai 8 meses
py.typed	1c988a48b2 fix logging and add py.typed	hai 1 ano