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). @ 0f4a9ee77be8a5a4a58d8a13d66eaab4e42bcf9e

AlpinDale 3a0fdf7b9b chore: remove `image_input_type` from VLM config		7 hónapja
..
chat_templates	e1c4cf1d50 chore: organize chat templates	7 hónapja
fp8	d63690a0df chore: add fp8 examples	7 hónapja
marlin	e42a78381a feat: switch from pylint to ruff (#322)	1 éve
monitoring	b1555eb208 add new grafana metrics	7 hónapja
offline_inference	1852d18326 chore: clean up inference examples	7 hónapja
vision	3a0fdf7b9b chore: remove `image_input_type` from VLM config	7 hónapja
aphrodite_engine_example.py	f32d57ed04 add inference examples	1 éve
api_client.py	f32d57ed04 add inference examples	1 éve
gguf_to_torch.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 hónapja
gradio_server.py	e42a78381a feat: switch from pylint to ruff (#322)	1 éve
save_sharded_state.py	7bcff4ac03 implement sharded state dict	7 hónapja
tensorize_aphrodite_model.py	d0cca80b8b feat: support sharded tensorizer models	7 hónapja