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). @ feat/tree-attention

sgsdxzy 58b0616dd3 feat: support sharded ggufs (#420)		8 mēneši atpakaļ
..
marlin	e42a78381a feat: switch from pylint to ruff (#322)	10 mēneši atpakaļ
monitoring	070c1cef8c fix: explicit RFC3986 for prometheus_client asgi (#344)	9 mēneši atpakaļ
alpaca_template.jinja	2755a48d51 merge dev branch into main (#153)	1 gadu atpakaļ
aphrodite_engine_example.py	f32d57ed04 add inference examples	1 gadu atpakaļ
api_client.py	f32d57ed04 add inference examples	1 gadu atpakaļ
chatml_template.jinja	2755a48d51 merge dev branch into main (#153)	1 gadu atpakaļ
gguf_to_torch.py	58b0616dd3 feat: support sharded ggufs (#420)	8 mēneši atpakaļ
gradio_server.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mēneši atpakaļ
offline_inference.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mēneši atpakaļ
prefix_cache_example.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	11 mēneši atpakaļ
pygchat_template.jinja	80e8a14949 feat: add pygchat Jinja template (#218)	11 mēneši atpakaļ
slora_inference.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mēneši atpakaļ