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). @ e13a66925cf2d117b26d0e062e2c62f82dc7f7dd

AlpinDale e13a66925c feat: add fuyu vision model and persimmon language model support		6 ヶ月前
..
chat_templates	e1c4cf1d50 chore: organize chat templates	7 ヶ月前
fp8	d63690a0df chore: add fp8 examples	7 ヶ月前
marlin	e42a78381a feat: switch from pylint to ruff (#322)	1 年間前
monitoring	b1555eb208 add new grafana metrics	7 ヶ月前
offline_inference	a3b56353fa fix: another one missed	6 ヶ月前
vision	e13a66925c feat: add fuyu vision model and persimmon language model support	6 ヶ月前
aphrodite_engine_example.py	f32d57ed04 add inference examples	1 年間前
api_client.py	f32d57ed04 add inference examples	1 年間前
gguf_to_torch.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 ヶ月前
gradio_server.py	e42a78381a feat: switch from pylint to ruff (#322)	1 年間前
save_sharded_state.py	7bcff4ac03 implement sharded state dict	7 ヶ月前
tensorize_aphrodite_model.py	d0cca80b8b feat: support sharded tensorizer models	7 ヶ月前