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).

AlpinDale 6212072245 api: support LoRA lineage and base model metadata management (#1072)		vor 5 Tagen
..
ops	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	vor 2 Wochen
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	vor 11 Monaten
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
layers.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	vor 4 Monaten
lora.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
models.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	vor 5 Tagen
punica.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	vor 2 Wochen
request.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	vor 5 Tagen
utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
worker_manager.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten