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). @ 80be38ca6f43f03bcb6b3946c454fe2d965c9704

AlpinDale 6d8df254c7 LoRA: skip loading unsupported weight modules (#1109)		1 settimana fa
..
ops	69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104)	1 settimana fa
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	1 anno fa
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mesi fa
layers.py	1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671)	4 mesi fa
lora.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mesi fa
models.py	6d8df254c7 LoRA: skip loading unsupported weight modules (#1109)	1 settimana fa
punica.py	69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104)	1 settimana fa
request.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	1 mese fa
utils.py	6d8df254c7 LoRA: skip loading unsupported weight modules (#1109)	1 settimana fa
worker_manager.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mesi fa