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). @ ea0f57b23361867fef38f17f75225dd4b8679926

AlpinDale ea0f57b233 feat: allow further support for non-cuda devices (#247)		1 年間前
..
common	ea0f57b233 feat: allow further support for non-cuda devices (#247)	1 年間前
endpoints	d2db4143fa feat: add grafana for metrics (#240)	1 年間前
engine	ea0f57b233 feat: allow further support for non-cuda devices (#247)	1 年間前
lora	c0aac15421 feat: S-LoRA support (#222)	1 年間前
modeling	ea0f57b233 feat: allow further support for non-cuda devices (#247)	1 年間前
processing	c0aac15421 feat: S-LoRA support (#222)	1 年間前
task_handler	ea0f57b233 feat: allow further support for non-cuda devices (#247)	1 年間前
transformers_utils	c0aac15421 feat: S-LoRA support (#222)	1 年間前
__init__.py	9f77f35ff5 bump version to 0.4.6 (#204)	1 年間前
py.typed	1c988a48b2 fix logging and add py.typed	1 年間前