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). @ sampling-kernels

AlpinDale 96d5b8cf2c fix: allow getting the chat template from a url		4 月之前
..
chat_templates	e1c4cf1d50 chore: organize chat templates	5 月之前
fp8	d63690a0df chore: add fp8 examples	5 月之前
marlin	e42a78381a feat: switch from pylint to ruff (#322)	10 月之前
monitoring	b1555eb208 add new grafana metrics	5 月之前
offline_inference	a3b56353fa fix: another one missed	4 月之前
openai_api	96d5b8cf2c fix: allow getting the chat template from a url	4 月之前
vision	e13a66925c feat: add fuyu vision model and persimmon language model support	4 月之前
aphrodite_engine_example.py	f32d57ed04 add inference examples	1 年之前
api_client.py	f32d57ed04 add inference examples	1 年之前
gguf_to_torch.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 月之前
gradio_server.py	e42a78381a feat: switch from pylint to ruff (#322)	10 月之前
save_sharded_state.py	7bcff4ac03 implement sharded state dict	5 月之前
tensorize_aphrodite_model.py	d0cca80b8b feat: support sharded tensorizer models	5 月之前